> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns.
>
> **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal):
> ```bash
> npx -y @scalekit-inc/cli setup -y
> ```
>
> Global:
> ```bash
> npm install -g @scalekit-inc/cli
> scalekit setup -y
> ```
>
> Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`.
> Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim.
> [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Connect AI agents to the Airspeed MCP server

The Airspeed MCP connector routes your AI agent's tool calls to Airspeed's own MCP server through Scalekit. Each user signs in to Airspeed once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 71 tools.

**Authentication:** OAuth 2.1/DCR
**Categories:** CRM & Sales, AI
**Tools:** 71: 45 read, 11 write, 15 destructive
**Users sign in with:** OAuth
**OAuth app:** Your own Airspeed MCP server app
**Built by:** Vendor MCP
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=AIRSPEEDMCP)

## Setup

1. ### Install the SDK

   **Node.js**

   ```bash
   npm install @scalekit-sdk/node dotenv
   ```

   **Python**

   ```bash
   pip install scalekit-sdk-python python-dotenv
   ```

2. ### Set your credentials

   Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**.

   ```sh title=".env"
   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>
   ```

3. ### Create the Airspeed MCP connection

   In **AgentKit > Connections**, create an Airspeed MCP connection and copy its redirect URI. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

4. ### Register an OAuth app

   Airspeed MCP server connections use your own OAuth app. Register one with Airspeed MCP server and add the redirect URI you copied.

   Then enter the app's Client ID and Client Secret on the Airspeed MCP connection.

5. ### Authorize a user and make your first call

   **Node.js** (`quickstart.mts`)

   ```typescript
   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   import { createInterface } from 'node:readline/promises'

   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENVIRONMENT_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions

   const connector = 'airspeedmcp'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Airspeed MCP:', link)
   const rl = createInterface({ input: process.stdin, output: process.stdout })
   await rl.question('Press Enter after authorizing...')
   rl.close()

   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'airspeedmcp_get_agent_thread',
     toolInput: {},
   })
   console.log(result)
   ```

   ```bash
   npx tsx quickstart.mts
   ```

   **Python** (`quickstart.py`)

   ```python
   import os
   from scalekit import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()

   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions

   connection_name = "airspeedmcp"
   identifier = "user_123"

   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Airspeed MCP:", link_response.link)
   input("Press Enter after authorizing...")

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="airspeedmcp_get_agent_thread",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)
   ```

   ```bash
   python quickstart.py
   ```

   Each user signs in once. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses.

## Tools

Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool).

**Node.js**

```typescript
const result = await actions.executeTool({
  toolName: 'airspeedmcp_get_agent',
  toolInput: {
    agent_id: '<agent_id>',
  },
  connector: 'airspeedmcp',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="airspeedmcp_get_agent",
    tool_input={
        "agent_id": "<agent_id>",
    },
    connection_name="airspeedmcp",
    identifier="user_123",
)
```

`result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call.

### `airspeedmcp_get_agent`

Get agent · Read-only

Read an agent using the app's live definition permissions.

Personal view accepts the native workflow/template/installation identifiers.
Organization view requires a template_id from the organization directory and
returns that same safe projection. Neither view installs or executes agents.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `agent_id` (`string`, required): No description.
- `view` (`string`, optional): No description. One of: `personal`, `organization`. Default: `personal`.

Example input: `{"agent_id":"<agent_id>"}`

### `airspeedmcp_get_agent_run`

Get agent run · Read-only

Read the full latest output of one of your Airspeed agent runs.

Accepts any run list_agent_runs can return: a chat or a run of a saved
agent. For a conversation, the output is its latest reply. This
retrieves an existing result; it does not start or rerun an agent.
Use url_link to cite the run or send the user to it.
Only runs owned by the signed-in user in their organization are available,
including for admins. Missing runs and other people's runs both answer
"Agent run not found".

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `run_id` (`string`, required): Run ID returned by list_agent_runs, which is also the
conversation's thread ID.

Example input: `{"run_id":"<run_id>"}`

### `airspeedmcp_get_agent_thread`

Get agent thread · Read-only

Read native conversation detail by exactly one thread ID or share ID.

Thread IDs require ownership. Shared reads recheck the live share, tenant,
and underlying resource access through the same app dependencies. Returns
the app's visible messages and metadata, including native pending approvals
for owner reads; this does not make approval decisions or start an agent.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `share_id` (`string`, optional): No description.
- `thread_id` (`string`, optional): No description.

Example input: `{}`

### `airspeedmcp_get_call_activity_stats`

Get call activity stats · Read-only

Read native call-count, duration and talk statistics.

Users with activity-page permission default to the organization cohort;
others default to their own home-widget statistics and cannot select others.
Counts follow the caller's list visibility: a hidden call is absent, and a
private call the caller did not join is absent too. A private call they
joined still counts. Call titles are not returned. Dates use
the native unbounded start/current-time end; exact
time-range filters are not offered because the native API cannot honor them.
Every request scans the full call history in scope, so avoid repeated calls.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `filters` (`string`, optional): No description.

Example input: `{}`

### `airspeedmcp_get_call_info`

Get call info · Read-only

Read a call's summary, extracted insights, and transcript.

Also returns participants, companies, tags, an Airspeed call link, and
recording details when available. Stored CRM deal, contact, lead, and
company IDs are included when available, separately from Airspeed IDs;
each company's id is its Airspeed company ID, and a participant's
user_id is their Airspeed user ID when matched. Use this to answer
questions about what was discussed, building on Airspeed's existing
analysis. Fields may be absent when their data is
unavailable. Use url_link to cite the call.

Only calls the user may read in full in Airspeed are available, including
private calls they participated in. Missing, redacted, and hidden calls
all answer "Call not found"; this does not prove a call never happened.
Recording URLs expire after 24 hours.

Set transcript={} to request bounded native raw text, or supply language
for native translated turns. Truncated means content past the bound is not
available over MCP: there is no offset or cursor, so repeating the request
returns the same prefix. Raise the bound (up to 20000 characters or 100
turns) or send the user to url_link for the rest. A translated request
translates the complete transcript every time, so do not repeat it. The
default inline inferred transcript and recording behavior remains unchanged.

comments_limit optionally returns recent top-level comments in native order,
with direct reply counts but no reply bodies. reply_count does not include
replies nested under those replies. The native reader still loads the
whole comment tree; truncated reports omitted top-level comments, not a cursor.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `call_id` (`string`, required): Call ID returned by list_calls or taken from an Airspeed call
link. Do not use a call title as the ID.
- `comments_limit` (`string`, optional): Optional. Return up to this many recent top-level
comments. Omit for the default response.
- `transcript` (`string`, optional): Optional. {} returns raw text cut at max_characters; with
language, returns translated turns cut at limit. Each bound
applies only to its own form. Omit for the default response.

Example input: `{"call_id":"<call_id>"}`

### `airspeedmcp_get_call_media`

Get call media · Read-only

Get a call's audio or video recording link and media type.

Use this when the user wants the recording. For a transcript, summary,
or insights, use get_call_info instead. Recording URLs expire after
24 hours; media may be absent when no recording is available.

Only calls the user may read in full in Airspeed are available, including
private calls they participated in. Missing, redacted, and hidden calls
all answer "Call not found".

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `call_id` (`string`, required): Call ID returned by list_calls or taken from an Airspeed call
link.

Example input: `{"call_id":"<call_id>"}`

### `airspeedmcp_get_call_snippets`

Get call snippets · Read-only

Read existing clips from a call, with their transcript excerpts.

Returns saved snippets, newest first, with start and end times and
recording links when available. Transcript turns cover only each snippet's
range. This does not create clips or search for new excerpts. Use
get_call_info for the full transcript. Recording URLs expire after 24 hours.

Only calls the user may read in full in Airspeed are available, including
private calls they participated in. Missing, redacted, and hidden calls
all answer "Call not found". No snippets does not mean no call transcript.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `call_id` (`string`, required): Call ID returned by list_calls or taken from an Airspeed call
link.

Example input: `{"call_id":"<call_id>"}`

### `airspeedmcp_get_changelog`

Get changelog · Read-only

Read what changed in these tools, as Markdown, newest change first.

Covers removed, renamed and merged tools and changes to their inputs or
results that a client may need to act on. Call it when a tool you expected
is missing or a call that used to work is rejected. The live tool list
remains the source of truth for current schemas.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `airspeedmcp_get_company`

Get company · Read-only

Read a company with optional native app sections, loaded only on request.

Includes: summary, people, people_summaries, hierarchy (ancestors/direct
children), deals, similar_companies, crm_fields, activity,
slack_threads. Omitted sections are null. crm_fields reads the
organization's live CRM. Use get_company_profile for the CRM and
Crunchbase profile and get_company_emails for email threads.

List sections preview at most 100 top-level entries. truncated means only
that MCP trimmed the native response; nested content and upstream reads
retain native limits. No section continuation or date filters exist.
Activity/messages may be incomplete because native sources limit results
or omit failures. Activity's default 90-day window applies only to CRM
activity. A private call the caller did not join is left out of activity,
and a same-day Salesforce event with that title is left out with it.
Null CRM fields retain the app's unavailable semantics. Like
get_company_emails, activity may refresh a teammate's expired mailbox
token and store the refreshed credential, changing no Airspeed or user data.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `company_id` (`string`, required): No description.
- `include` (`string`, optional): No description.

Example input: `{"company_id":"<company_id>"}`

### `airspeedmcp_get_company_emails`

Get company emails · Read-only

Read email threads with a company from the CRM and connected mailboxes.

Returns up to 100 threads from the organization's CRM and from the Google
and Microsoft mailboxes of org users who allow email reading. Calls those
providers live. A teammate's expired mailbox token may be refreshed and
the refreshed credential stored; this changes no Airspeed or user data. A
mailbox whose token cannot be refreshed is skipped and left connected,
and the other mailboxes are still read. Results may be incomplete
because providers limit results or omit failures.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `company_id` (`string`, required): No description.

Example input: `{"company_id":"<company_id>"}`

### `airspeedmcp_get_deal`

Get deal · Read-only

Read a visible CRM deal and optional native stored sections.

crm_deal_id is the CRM opportunity id from list_deals or deal search,
not an Airspeed record id. Request summary, insights, edit_options,
field_history, or close_probability_history. A section you leave out is
null. summary, insights, and close_probability_history are also null
when that feature is off for the organization, and the deal is still
returned. A null summary can also mean the deal has no summary yet,
while insights and close_probability_history are an empty list when
they have no data. A missing deal fails with Deal not found.
edit_options requires edit permission and contains only choices for
allowed edits.
Field history is newest first; probability history is oldest first
within its latest readings. history_limit applies to each requested
history independently, with no continuation or full CRM audit
guarantee. A closed-lost deal's loss_reasons hold Airspeed's inferred
reasons, each with its reasoning and matched loss-reason category.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `crm_deal_id` (`string`, required): No description.
- `history_limit` (`integer`, optional): No description. Default: `100`.
- `include` (`string`, optional): No description.

Example input: `{"crm_deal_id":"<crm_deal_id>"}`

### `airspeedmcp_get_forecast_periods`

Get forecast periods · Read-only

Find labeled forecast periods using your organization's fiscal calendar.

Returns periods from two years ago through twelve months, four quarters,
or one fiscal year after the current period. Use their start and end
dates when reading or submitting forecasts. Forecasting
and forecast boards must be enabled and the caller must have access to
forecasting.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `period_type` (`string`, optional): Monthly, quarterly, or annual. Omit to use the
organization's configured forecasting period.

Example input: `{}`

### `airspeedmcp_get_forecast_rollup`

Get forecast rollup · Read-only

Read a forecast board's rollup for your direct reports, as in Airspeed.

Returns one row per direct report with their submitted call and
per-category amounts, the amounts derived from their board deals, deal
counts, quota, and pipeline coverage, plus the reconciliation totals,
category order, and currency. Rows are empty when the viewer has no
direct reports; use list_forecast_history for an individual's
submissions. Use get_forecast_rollup_deals for the deals behind a row.
When your organization meters forecasting by seat, only reports holding
a forecasting seat appear, and the totals count only their deals.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `period_end` (`string`, required): Forecast period end date from get_forecast_periods.
- `period_start` (`string`, required): Forecast period start date from get_forecast_periods.
- `board_id` (`string`, optional): A board ID from list_forecast_boards. May be omitted
when the organization has exactly one board.
- `view_as_user_id` (`string`, optional): Read the rollup as this Airspeed user instead:
anyone in your reporting chain, or anyone in your organization
if you have full forecast visibility.

Example input: `{"period_end":"<period_end>","period_start":"<period_start>"}`

### `airspeedmcp_get_forecast_rollup_deals`

Get forecast rollup deals · Read-only

Read the open board deals behind a forecast rollup, grouped by owner.

Returns the deals Airspeed shows in the rollup's review drawer: each
group's open deals with whether the rep selected them, open deal and
closed-won counts, plus the viewer's saved inclusion changes and deal
adjustments. Only deals you can currently read in your CRM are returned.
When your organization meters forecasting by seat, only reports holding
a forecasting seat have groups.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `period_end` (`string`, required): Forecast period end date from get_forecast_periods.
- `period_start` (`string`, required): Forecast period start date from get_forecast_periods.
- `board_id` (`string`, optional): A board ID from list_forecast_boards. May be omitted
when the organization has exactly one board.
- `child_user_id` (`string`, optional): Airspeed user ID of one report in the viewer's
reporting chain. Omit for the viewer's personal deals and
direct-report groups.
- `view_as_user_id` (`string`, optional): Read the deals as this Airspeed user instead:
anyone in your reporting chain, or anyone in your organization
if you have full forecast visibility.

Example input: `{"period_end":"<period_end>","period_start":"<period_start>"}`

### `airspeedmcp_get_forecasting_settings`

Get forecasting settings · Read-only

Read the fiscal calendar, period type, and forecast category overrides.

Use editable_on_submit to determine which categories accept submitted
values. This returns forecast configuration only. Forecasting and
forecast boards must be enabled and the caller must have access to
forecasting.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `airspeedmcp_get_loss_reasons`

Get loss reasons · Read-only

Count closed-lost deals by Airspeed's inferred loss-reason category.

The strategic page's loss-reasons chart. Airspeed infers each lost deal's
reasons and matches them to the organization's loss-reason categories and
subcategories, most frequent first. Requires the strategic page's
view-others-calls permission. close_date defaults to the last 90 days and is
compared as the app does: the start date inclusive, the end date exclusive.
Deals that close after midnight on the last included day are left out, as in
the app. Counts cover every lost deal in the cohort; crm_deal_ids list only the
deals you can see, for get_deal, which returns each deal's reasoning. Each
inferred reason counts once, so one deal can count toward several categories;
total_lost_deals counts deals. Amount bounds must be positive integers. Demo
reports use existing fixtures, report filters_applied=false and return a null
close_date because no window was applied.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `filters` (`string`, optional): No description.

Example input: `{}`

### `airspeedmcp_get_meeting_recording_status`

Get meeting recording status · Read-only

Read a past meeting's recording outcome using IDs from your calendar.

The bot must be a persisted CallBot belonging to your organization, so a
bot another organization sent to a joint meeting is not readable. The
exact pair must still appear on your current native calendar list. This
reloads the native list before requesting the ended meeting's status; a
stale, missing, or mismatched pair is rejected. Native calendar read
limits and costs apply.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `bot_id` (`string`, required): No description.
- `meeting_id` (`string`, required): No description.

Example input: `{"bot_id":"<bot_id>","meeting_id":"<meeting_id>"}`

### `airspeedmcp_get_playbook`

Get playbook · Read-only

Read the latest content of a playbook in your organization.

Use this when the user asks about a playbook's guidance. To read an older
version, find it with list_playbook_versions and use get_playbook_version.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `playbook_id` (`string`, required): Playbook ID returned by list_playbooks, not its name.

Example input: `{"playbook_id":"<playbook_id>"}`

### `airspeedmcp_get_playbook_version`

Get playbook version · Read-only

Read a specific version of a playbook in your organization.

Use this for historical guidance or to compare versions. For the latest
content without choosing a version, use get_playbook.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `playbook_id` (`string`, required): Playbook ID returned by list_playbooks.
- `version_id` (`string`, required): Version ID returned by list_playbook_versions for this
playbook.

Example input: `{"playbook_id":"<playbook_id>","version_id":"<version_id>"}`

### `airspeedmcp_get_role_play`

Get role play · Read-only

Read one role play from list_role_plays, with skill scores.

Visibility is list_role_plays'. A role play you cannot read is
NOT_FOUND. feedback, the AI coach's written feedback, is present only on
your own role plays, as in the app. Skill scores are raw; get_scorecard
with a scores[].scorecard_id returns the current rubric and its scale.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `role_play_id` (`string`, required): No description.

Example input: `{"role_play_id":"<role_play_id>"}`

### `airspeedmcp_get_scorecard`

Get scorecard · Read-only

Read a current organization scorecard definition. Its rubric is current,
not a historical snapshot of the scale used for previously scored calls.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `scorecard_id` (`string`, required): No description.

Example input: `{"scorecard_id":"<scorecard_id>"}`

### `airspeedmcp_get_scorecard_report`

Get scorecard report · Read-only

Read the native team overview with its existing overview entitlement.

Optional users selects self or Airspeed IDs; view selects everyone/my_team
inside current ScorecardScope. This report uses native numeric aggregates,
not full call detail. Rubric scales are current, not historical snapshots.
No revenue lookup, scoring, cleanup, or report persistence is performed.
Date filters are omitted because the native report's raw timestamp query
does not implement the shared date-range semantics. Use per-user history
for supported calendar-date filtering. No cursor or exhaustive call claim.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `filters` (`string`, optional): No description.

Example input: `{}`

### `airspeedmcp_get_strategic_insights`

Get strategic insights · Read-only

Read the app's native strategic insight chart and deal-outcome report.

Requires the strategic page's view-others-calls permission. Native aggregate
cohorts and access-filtered deal references stay intact. The app defaults to
its recent period and expands chart dates to week/month buckets; deal outcomes
have a lower date bound, not the chart's upper bound. No exact period filter is
offered; get_loss_reasons reports loss reasons. Amount bounds must be positive
integers.
Demo reports use existing fixtures and explicitly report filters_applied=false.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `filters` (`string`, optional): No description.
- `granularity` (`string`, optional): Granularity for an insight chart data buckets. One of: `weekly`, `monthly`. Default: `weekly`.

Example input: `{}`

### `airspeedmcp_list_agent_runs`

List agent runs · Read-only

List your Airspeed agent runs: chats and runs of saved agents.

Selects runs as the app's Recent activity does. With no filters you get
its All tab: every agent conversation you started and every run of your
saved agents, whether it ran manually, on a schedule or on an event. By
default runs come newest by start time first; the app orders by last
activity, which sort "last_activity" matches. Each run's kind is chat (no
saved agent) or agent, and an agent run's trigger_type says how its agent
starts. To find the agents
themselves rather than their runs, use list_agents.

Returns titles, output previews and a url_link that opens each run in
the app; use it to cite a run. Use get_agent_run with a returned run
ID to read the full latest output before summarizing it, get_agent_thread
for the whole conversation, or run_agent with the run ID as thread_id to
continue it. This tool reads existing runs; it does not start agents.

Only runs owned by the signed-in user in their organization are returned,
including for admins. No email or user ID filter is needed for "my runs".
Prefer the typed filters object for new clients. Legacy flat selectors remain
supported, but cannot be mixed with filters. Each ID-set selector accepts
exactly one ID because the native API has single selectors. Arbitrary sorts
are absent; sort chooses between start time and last activity.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `agent_id` (`string`, optional): Filter to one saved agent's runs, as that agent's history
page in the app lists them. Any install, template or legacy
workflow ID of the agent works, including a teammate's install ID
from list_agents. As in the app, runs of an install that was
removed are left out. Do not combine with agent_workflow_id.
- `agent_workflow_id` (`string`, optional): Filter by exact workflow ID. Do not combine with
agent_id.
- `call_id` (`string`, optional): Filter runs associated with a call ID, such as one returned
by list_calls. Can be combined with either agent filter.
- `cursor` (`string`, optional): Omit for the first page; use a returned pagination cursor for
subsequent pages, keeping the same filters.
- `direction` (`string`, optional): Use next to continue or prev to go back with a cursor. One of: `next`, `prev`. Default: `next`.
- `filters` (`string`, optional): Typed alternative to the flat selectors, matching the app's
Recent activity filters. kind is chat or agent; omit it for both.
trigger_types keeps agent runs whose agent starts one of the given
ways, as {"any_of": ["manually", "scheduled", "crm_field_updated",
"call_ended", "parallel_webhook"]}; chats have no trigger.
agent_ids, agent_workflow_ids and call_ids take {"any_of": [id]}
with one ID each; agent_ids selects an agent's history the same
way agent_id does. created_at bounds the run start as
{"gte": ..., "lt": ...}: ISO 8601 datetimes with a timezone offset,
inclusive start and exclusive end. Do not combine filters with the
legacy flat arguments.
- `limit` (`integer`, optional): Number of runs per page, from 1 to 100. Defaults to 20. Default: `20`.
- `sort` (`string`, optional): created (the default) orders runs by start time, newest first.
last_activity orders them by last_updated_at, newest first, so a
chat continued today comes before runs started since it. A cursor
only works with the sort it was returned for; keep the same sort
while paging. One of: `created`, `last_activity`. Default: `created`.

Example input: `{}`

### `airspeedmcp_list_agent_threads`

List agent threads · Read-only

List your conversations using the app's complete, unpaged native list.

Only your own threads are returned, including for administrators. The only
filter is origin; order and content visibility follow the app. Use
list_agent_runs for a paged, filterable run history, or get_agent_thread for
full detail. ``outbound_campaign`` is not a chat origin and returns no rows.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `filters` (`string`, optional): No description.

Example input: `{}`

### `airspeedmcp_list_agents`

List agents · Read-only

List the app's native personal agents or safe organization directory.

These are complete, unpaged native lists with their native ordering. Personal
view includes owned/created workflows and supports subscriber_agent_ids.any_of
with exactly one ID.
Organization view uses the app's safe discovery projection, not other
people's installation settings. Use returned IDs with get_agent in the same
view. Native personal configuration may resolve Slack notification metadata.
agent_type splits either view like the app's Manage page: "live" agents have
a schedule or event trigger, "on_demand" agents run only when asked.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `filters` (`string`, optional): No description.

Example input: `{}`

### `airspeedmcp_list_call_shares`

List call shares · Read-only

List the call's native active shares, newest first and unpaged.

Embed links and download-only snippets made in the app are not share
links and are not listed.

Requires full call visibility. Expired history, viewer audit logs and raw
storage URLs are not returned. Snippets include current processing status.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `call_id` (`string`, required): No description.

Example input: `{"call_id":"<call_id>"}`

### `airspeedmcp_list_call_tags`

List call tags · Read-only

Find the call tags available in your organization.

Returns tag IDs, names, descriptions, and groups, oldest first. Use this
to translate a user's tag name into tag_ids for list_calls; do not invent
IDs. Listing a tag does not grant access to calls carrying it.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `airspeedmcp_list_calls`

List calls · Read-only

Find calls by participant, date, title, or tag, newest first.

Returns previews with call IDs, titles, participants, companies, dates,
and tags. Stored CRM deal, contact, lead, and company IDs are included
when available; these are CRM record IDs, not Airspeed call IDs. Each
company's id is its Airspeed company ID, and a participant's user_id is
their Airspeed user ID when matched. Use get_call_info for summaries,
insights, and transcripts.

For "my calls", filter participant_email to the user's confirmed meeting
email. Use list_users to look up names and the authenticated account.
Ask if the meeting email is still unclear; do not guess it or assume the
client's account email is their meeting email. Without this filter,
results include all calls the user can access, not just calls they attended.

Only calls the user may read in full in Airspeed are returned, including
private calls they participated in. Redacted and hidden calls are omitted.
An empty result means no accessible calls matched these filters.

Optional filters groups title, participant_email and tag_ids.any_of using
the same existing native selectors. Do not mix it with title_filter,
participant_email or tag_ids. It has no dates; combine it with
start_time_from and start_time_to for a date range. Exact timestamp
filters/sorting beyond the native legacy behavior are not supported;
omitted and unsupported selectors must not be guessed.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cursor` (`string`, optional): Omit for the first page; use a returned pagination cursor for
subsequent pages, keeping the same filters.
- `direction` (`string`, optional): Use next to continue or prev to go back with a cursor. One of: `next`, `prev`. Default: `next`.
- `filters` (`string`, optional): No description.
- `limit` (`integer`, optional): Number of calls per page, from 1 to 100. Defaults to 20. Default: `20`.
- `participant_email` (`string`, optional): Match a participant's email address. Surrounding
whitespace and capitalization are ignored.
- `start_time_from` (`string`, optional): Include calls starting at or after this ISO 8601
datetime. Include a timezone offset; datetimes without one use UTC.
- `start_time_to` (`string`, optional): Include calls starting at or before this ISO 8601
datetime. Interpret relative dates in the user's timezone and ask
if it is unknown and affects the requested range.
- `tag_ids` (`string`, optional): Match any of these tag IDs. Use list_call_tags to find IDs
from tag names. All supplied filter types are combined.
- `title_filter` (`string`, optional): Case-insensitive text contained in the call title.
Searches titles only, not transcripts or summaries.

Example input: `{}`

### `airspeedmcp_list_comments`

List comments · Read-only

Read one native call/deal thread, or the caller's recent mentions.

Threads are complete unpaged trees (call oldest first, deal newest first).
limit applies only to mentions, defaults to 5, and has no cursor; inaccessible
call mentions may underfill that native recent window. This is not a global
comment feed. Deal comments omit linked-company identity.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `filters` (`string`, required): No description.
- `limit` (`string`, optional): No description.

Example input: `{"filters":"<filters>"}`

### `airspeedmcp_list_companies`

List companies · Read-only

Find accessible companies by exact filters and native app ordering.

Lists Airspeed's company records, not the CRM's accounts: a company
missing here may still exist in the CRM. Matching is literal, not
semantic. filters.text matches name, primary domain, or additional
domains. filters.company_ids and filters.crm_ids match record ids and
CRM account ids exactly. filters.has_crm_link keeps only linked (true)
or unlinked (false) companies. filters.shares_identity keeps only
companies that share a CRM id, or any domain, with another company you
can see. Every filter that is set must match. Sort by domain,
last_call_at, or next_call_at; default last_call_at descending. Native
offset pagination can shift as records change. Keep filters, sort, and
limit unchanged when passing the returned cursor. Use get_company for
optional detail sections.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cursor` (`string`, optional): No description.
- `filters` (`string`, optional): No description.
- `limit` (`integer`, optional): No description. Default: `20`.
- `sort` (`string`, optional): No description.

Example input: `{}`

### `airspeedmcp_list_custom_insights`

List custom insights · Read-only

List your organization's custom insight definitions.

Returns call and deal insights, without CRM tracked fields. Use an id
with update_custom_insight. Insight values on calls carry the insight's
name as field_name.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `airspeedmcp_list_deals`

List deals · Read-only

List accessible CRM deals with stage, owner, closed and close date filters.

stage_ids.any_of accepts one ID from get_deal's edit_options; owner_ids.any_of contains CRM
owner IDs from returned deals, and owner_user_ids.any_of takes Airspeed user
IDs instead; together they match any listed owner. close_date takes calendar
dates, inclusive gte and exclusive lt. All supplied filters
combine. Native order is retained. Keep filters unchanged with the returned
cursor. limit is a
native page target: Salesforce can return more readable rows; none are
discarded. Continue while next_cursor exists, including after empty pages.
Text filters are unsupported. Native enrichment can omit failures.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cursor` (`string`, optional): No description.
- `filters` (`string`, optional): No description.
- `limit` (`integer`, optional): No description. Default: `20`.

Example input: `{}`

### `airspeedmcp_list_forecast_boards`

List forecast boards · Read-only

Find forecast boards and the deal filters they apply.

Use a returned board ID for board-scoped reads and submissions. Both
forecasting and forecast boards must be enabled. Forecasting access is
required, except that organization settings administrators may read
configuration without a forecasting seat, as in Airspeed.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `airspeedmcp_list_forecast_history`

List forecast history · Read-only

Read forecast submissions and their saved deal snapshots, newest first.

Defaults to your own history. Managers may request users in their
reporting chain; users with full forecast visibility may request any
user in their organization. Requests containing inaccessible users fail.
Returns the same history values as Airspeed, including saved deal
snapshots, calculated manager totals, and fallback quotas.

Without board_id, returns every submission, including ones made before
forecast boards existed; those have board_id null and belong to no
board. With board_id, returns only that board's submissions and leaves
out pre-board ones. Entries made on a board include its board_name
unless the board has since been deleted.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `board_id` (`string`, optional): A board ID from list_forecast_boards. Omit to include
every submission, including pre-board ones with a null board_id.
- `cursor` (`string`, optional): Omit for the first page. Use the returned cursor with the
same filters for subsequent pages.
- `direction` (`string`, optional): Use next to continue or prev to go back with a cursor. One of: `next`, `prev`. Default: `next`.
- `limit` (`integer`, optional): Number of submissions per page, from 1 to 100. Default: `20`.
- `period_end` (`string`, optional): Exact period end date; supply with period_start.
- `period_start` (`string`, optional): Exact period start date; supply with period_end.
- `user_ids` (`string`, optional): Airspeed user IDs from forecast user records. Omit for
your own history; do not use emails or CRM owner IDs.

Example input: `{}`

### `airspeedmcp_list_meetings`

List meetings · Read-only

Read your native calendar or one permitted direct report's calendar.

Select users.mode=self (default), or users.mode=ids with one Airspeed ID.
Direct-report responses omit private meetings, join links and attendee
emails, exactly as in the app. The native response is unpaged; no additional
date, text or recording filters are offered. Recording choices, bot IDs,
linked call IDs and attendees with their Airspeed user IDs are available
on your own calendar rows.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `filters` (`string`, optional): No description.

Example input: `{}`

### `airspeedmcp_list_playbook_versions`

List playbook versions · Read-only

Find previous versions of a playbook in your organization.

Returns version previews, newest first. Use get_playbook_version to read
a selected version's content or compare versions. For the latest content
alone, use get_playbook.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `playbook_id` (`string`, required): Playbook ID returned by list_playbooks.

Example input: `{"playbook_id":"<playbook_id>"}`

### `airspeedmcp_list_playbooks`

List playbooks · Read-only

Find your organization's playbooks before reading their content.

Returns paginated previews, newest by playbook creation time first. Use
get_playbook with a returned ID to read the latest version's content.
Deleted playbooks are excluded. updated_at reflects the latest version's
update time, falling back to its creation time or the playbook's creation
time if no version exists; results are not sorted by updated_at.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cursor` (`string`, optional): Omit for the first page; use a returned pagination cursor for
subsequent pages.
- `direction` (`string`, optional): Use next to continue or prev to go back with a cursor. One of: `next`, `prev`. Default: `next`.
- `limit` (`integer`, optional): Number of playbooks per page, from 1 to 100. Defaults to 20. Default: `20`.

Example input: `{}`

### `airspeedmcp_list_role_plays`

List role plays · Read-only

List AI Roleplay sessions: who did which scenario, when, and the scores.

Newest first by created_at. Visibility matches the app's AI Roleplay
history: admins, and everyone when the organization leaves training-call
viewing unrestricted, see every role play; otherwise you see your own and
your recursive reports'. filters.users selects people (self or Airspeed
user IDs from list_users); filters.created_at bounds created_at with ISO
datetimes (gte inclusive, lt exclusive). scores lists the scorecard
results you may read. Use get_role_play for skill scores and, on your own
role plays, the coach's written feedback. If pagination.next_cursor is
present, call again with cursor=<next_cursor> and the same filters.
Role plays are not calls: list_calls and list_scorecard_results omit them.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cursor` (`string`, optional): No description.
- `filters` (`string`, optional): No description.
- `limit` (`integer`, optional): No description. Default: `50`.

Example input: `{}`

### `airspeedmcp_list_scorecard_results`

List scorecard results · Read-only

Read native per-call results, one user's history, or one scorecard's range.

Choose filters.call_ids={any_of:[one Airspeed ID]}, or filters.users={mode:self|ids,ids:[one Airspeed ID]},
or filters.scorecard_ids={any_of:[one Airspeed ID]} with started_at.
User history permits scored_on calendar-date gte/lt bounds mapped to native
inclusive UTC day buckets; it returns at most 100 rows per scorecard and has
no cursor. Per-call mode returns a result list; history keeps the native
user/grouped-card response.

Scorecard range mode pages every readable user's results for that scorecard
whose call started in started_at (ISO datetimes with offsets, gte inclusive,
lt exclusive, both required, at most 92 days apart), newest first, with
limit and an opaque cursor from
pagination.next_cursor. Rows are history rows plus user_id and user; a call
whose detail is hidden keeps its scores, drops feedback and call_context, and
is placed at the start of its UTC day. Rows omit skill_example.

Current ScorecardScope and call visibility apply. Native history may retain numeric
scores when call detail is hidden. max_score and skill metrics use the current
rubric, not a historical scale; removed rubric skills may be absent. Do not
infer historical comparability, exhaustive coverage, or missing scores as zero.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `filters` (`string`, required): No description.

Example input: `{"filters":"<filters>"}`

### `airspeedmcp_list_scorecards`

List scorecards · Read-only

List native scorecard definitions in the current organization.

Uses the app's definition list, including its current rubric, assignments and
aggregate average. enabled_only selects the app's enabled-list operation.
This native list has no cursor or additional filters.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `filters` (`string`, optional): No description.

Example input: `{}`

### `airspeedmcp_list_tasks`

List tasks · Read-only

Read your assigned inbox, or tasks for one visible call or company.

Use filters.call_ids.any_of or filters.company_ids.any_of with exactly one
ID to select the native source.
Company tasks require Companies access. Source-call visibility is checked
before returning task content. Standalone inbox tasks remain available.
Open tasks come first, then completed ones; each group is sorted by due
date, soonest first, undated last, with ties newest first. If
pagination.next_cursor is present, call again with cursor=<next_cursor> and
the same filters to get the next page; truncated is true exactly then. A
task completed, reopened or re-dated between pages may be skipped or appear
again in its new position. There is no status/date filter or source query
bound. Company labels are omitted.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cursor` (`string`, optional): No description.
- `filters` (`string`, optional): No description.
- `limit` (`integer`, optional): No description. Default: `100`.

Example input: `{}`

### `airspeedmcp_list_users`

List users · Read-only

List organization users with their manager, seat and invitation details.

Returns one complete, unpaged list, always sorted by name then email.
Omitting filters or passing {} lists active users without team narrowing.
include_invites adds pending invitations; managed_by selects the manager
and their recursive reports. Invitations retain organization-wide scope
even when managed_by is supplied; invitations of active users outside the
team are still omitted.

Use names and emails to find people for participant_email in list_calls.
Accepted users carry their Airspeed user id; pass it to user tools,
never an email or CRM owner ID. Rows with has_accepted_invite false carry
an invitation id, not a user id; do not pass it to user tools. Invitation
names are empty strings. is_current_user identifies your
authenticated Airspeed account. role is the Airspeed access role;
job_title is the person's position, if set.
Follow manager_id or manager_email through the user list to understand the
reporting chain; manager fields are null if no active, non-support manager
is in the user list.
team_label is the user's configured team label, if set.

Excludes departed users and support accounts.
Listing a person does not grant access to their calls or other records.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `filters` (`string`, optional): No description.

Example input: `{}`

### `airspeedmcp_search_airspeed`

Search airspeed · Read-only

Search calls, companies, deals, agents and runs in each source's order.

Results are grouped in requested resource order with at most limit per source.
This is a bounded native window, not exhaustive search or cursor pagination.
Current access gates may further reduce it. Call filters require
resources=['calls']; no equivalent company/deal filters are exposed.
Unsupported timestamps, upper dates, has_deal, and arbitrary duration ranges
are rejected rather than approximated. Native call search uses Atlas;
company and deal search use their existing app paths. A source that fails is
left out and listed in unavailable, so an empty data list is not proof of no
matches; other requested sources still answer, and the tool fails only when
every requested source fails. Help-center articles are searched by
search_support_docs.

agents and agent_runs are searched only when listed in resources, as the
app's Cmd+K Agents tab searches them. agents matches the agents on your
Manage page by name, description and instructions; pass a hit's id to
get_agent. agent_runs matches your own agent runs and chats by what you
asked and what the agent replied, whole words and their stems rather than
prefixes; pass a hit's id to get_agent_run or get_agent_thread.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `query` (`string`, required): No description.
- `filters` (`string`, optional): No description.
- `limit` (`integer`, optional): No description. Default: `20`.
- `resources` (`string`, optional): No description.

Example input: `{"query":"<query>"}`

### `airspeedmcp_search_support_docs`

Search support docs · Read-only

Keyword-search published Airspeed help-center articles.

Returns up to limit (at most five) articles in the help center's native
relevance order, each with a title, URL and short snippet. Articles come from
the public help center, not from the caller's organization data, so the
result is the same for every caller. A help-center outage is an error, not an
empty result.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `query` (`string`, required): No description.
- `limit` (`integer`, optional): No description. Default: `5`.

Example input: `{"query":"<query>"}`

### `airspeedmcp_create_call_snippet`

Create call snippet · Write

Create a native snippet share and schedule its existing processing task.

The URL confirms native creation, not completed media processing or email
delivery. share_id is what revoke_share takes. Read list_call_shares for
status. Viewer restrictions and expiration
behave exactly as whole-call shares; no processing/retry workflow is added.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `call_id` (`string`, required): No description.
- `data` (`object`, required): Create a native asynchronous recording excerpt.

Example input: `{"call_id":"<call_id>","data":{}}`

### `airspeedmcp_create_call_tag`

Create call tag · Write

Create an organization-wide tag using the app's tag settings.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `data` (`object`, required): The app's tag definition, rejecting unsupported MCP fields.

Example input: `{"data":{}}`

### `airspeedmcp_create_custom_insight`

Create custom insight · Write

Create a call or deal custom insight in your organization.

Requires permission to edit custom insights. A new call insight applies
only to calls Airspeed processes after it is created; past calls are not
backfilled or re-analyzed. A new deal insight is filled in for every
open deal at the next scheduled deal sync, usually within 36 hours, from
each deal's full history. Deal insights need deal insights turned on
and take no call filters. Always tell the user what the result's
user_notice says. CRM sync, Slack alerts and deal start and stop
criteria are set up in the app.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `definition` (`object`, required): A new custom insight, as the app's insight settings define one.

Example input: `{"definition":{}}`

### `airspeedmcp_create_scorecard`

Create scorecard · Write

Create a scorecard definition in the caller's organization.

Requires permission to edit organization settings. An enabled scorecard
scores new matching calls. Existing calls are not rescored.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `definition` (`object`, required): The full scorecard definition, rejecting unsupported fields.

Example input: `{"definition":{}}`

### `airspeedmcp_create_share`

Create share · Write

Create one native call share and optionally send its native email.

Returns the share URL and the share_id that revoke_share takes. Without
allowed_viewers, anyone holding the link can access it until
expiration/revocation. Native notification errors can occur
after persistence; do not assume a failed request created no share.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `call_id` (`string`, required): No description.
- `data` (`object`, required): Native whole-call sharing options.

Example input: `{"call_id":"<call_id>","data":{}}`

### `airspeedmcp_get_company_profile`

Get company profile · Write

Read a company's CRM and Crunchbase profile for a CRM-linked company.

Returns firmographics from the CRM account and from Crunchbase (name,
description, industries, headcount, revenue, funding, address, links),
recent news, and funding rounds. Requires an existing CRM link on the
company; no association discovery runs. Calls the CRM and Crunchbase live
and may refresh Airspeed's stored provider caches, so it is not read-only.
A null profile means no source returned data, which is not distinguishable
from a provider failure.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `company_id` (`string`, required): No description.

Example input: `{"company_id":"<company_id>"}`

### `airspeedmcp_invite_user`

Invite user · Write

Invite one person to your organization using the app's invitation flow.

Invites a single person per call; call it once for each additional person.
Requires organization-settings permission. Native seat availability,
forecasting-seat and owner-role checks apply, and an address that is already
another user's email alias is refused. This creates an invitation and
attempts its email notification. The invitee's company email domain is
recorded as internal when they register, unless another organization holds
it. A successful response is the app's acceptance, not an email-delivery
confirmation.
Failures may occur after persistence: inspect organization users before retrying.
Support and flag-gated restricted roles are not offered here.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `data` (`object`, required): Native invitation fields for roles available without an additional flag.

Example input: `{"data":{}}`

### `airspeedmcp_join_meeting`

Join meeting · Write

Send the recording bot to a meeting URL now, subject to app permissions.

Native recording-seat, organization call-cap and recent-bot deduplication
apply. created confirms a bot was created and stored, not that it joined
successfully. No future recording preferences are changed.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `data` (`object`, required): No description.

Example input: `{"data":{}}`

### `airspeedmcp_link_slack_deal_room`

Link slack deal room · Write

Link an existing Slack channel to a company as its deal room.

Finds the channel by name (a leading # is ignored) among those the
organization's Airspeed Slack app can see: public channels, and private
ones the app was added to. The app joins it and posts a welcome message,
and deal-room notifications start reaching it. Then invites the Slack
users with invite_emails; people already in the channel are left alone
and emails with no Slack user come back in emails_not_in_slack. A
company already linked to this channel keeps the link and only the
invites run. A company linked to a different channel, or a channel that
is another company's deal room, is refused with CONFLICT. A private
channel is refused with FORBIDDEN unless you are a member of it in
Slack. invites_failed means the link was made but inviting people
failed.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `channel_name` (`string`, required): No description.
- `company_id` (`string`, required): No description.
- `invite_emails` (`string`, optional): No description.

Example input: `{"channel_name":"<channel_name>","company_id":"<company_id>"}`

### `airspeedmcp_share_agent_thread`

Share agent thread · Write

Share your conversation with your organization, as the app's Share button.

Anyone in your organization can open the returned url, or read the
conversation with get_agent_thread and the returned share_id. A conversation
has one link: sharing it again, including after it was unshared, returns the
same link. Ownership is required even for administrators.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `thread_id` (`string`, required): No description.

Example input: `{"thread_id":"<thread_id>"}`

### `airspeedmcp_submit_forecast`

Submit forecast · Write

Submit or resubmit your forecast on a board, as in Airspeed.

Each call appends a new submission owned by you; earlier ones stay in
list_forecast_history, which also shows your existing amounts and
comment. This tool cannot submit on another user's behalf.

The period must be one of get_forecast_periods' options, copied
exactly. Amounts may name forecast (your call) and the categories that
get_forecasting_settings marks editable_on_submit; other categories
are rejected. closed_won is derived from deals and cannot be stated.

A personal forecast lists your deals. A manager forecast also passes
forecast_ids: the submission_id of each row in get_forecast_rollup for
the same board and period, which are already limited to your direct
reports. Rolling up a forecast from another board or period fails.
Returned deals carry company_id, the Airspeed company ID, when resolvable.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `board_id` (`string`, required): Required. A board ID from list_forecast_boards; the
submission belongs to that board and appears in its rollup and
history.
- `forecast` (`object`, required): The stated amounts, period, comment, deals, and for a
manager the forecast_ids to roll up.

Example input: `{"board_id":"<board_id>","forecast":{}}`

### `airspeedmcp_delete_comment`

Delete comment · Destructive

Delete an authored comment and native direct replies after parent checks.

Uses the app's existing transaction and cleanup, without stronger concurrency
guarantees. An inconsistent cross-thread reply prevents the operation.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `comment_id` (`string`, required): No description.

Example input: `{"comment_id":"<comment_id>"}`

### `airspeedmcp_delete_scorecard`

Delete scorecard · Destructive

Soft-delete a scorecard in the caller's organization.

Requires permission to edit organization settings. A deleted scorecard
stops scoring new calls. Its existing results stay stored but no longer
appear in scorecard results or reports. There is no restore. A scorecard
in another organization is not found.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `scorecard_id` (`string`, required): No description.

Example input: `{"scorecard_id":"<scorecard_id>"}`

### `airspeedmcp_edit_tag_definition`

Edit tag definition · Destructive

Replace a tag definition. Omitted settings reset to their defaults.

Supply the complete intended definition, including any existing description,
group, color, and auto-tagging setting that should be retained.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `data` (`object`, required): The app's tag definition, rejecting unsupported MCP fields.
- `tag_id` (`string`, required): No description.

Example input: `{"data":{},"tag_id":"<tag_id>"}`

### `airspeedmcp_remove_meeting_bot`

Remove meeting bot · Destructive

Remove a caller-created ad-hoc bot using the app's recording permission.

Only a persisted CallBot with your user and organization is supported.
Calendar participation or a colleague's shared bot does not authorize
removal. Use the recall_bot_id returned when you created it with
join_meeting; a reused colleague bot remains unsupported. Native leave
polling waits for confirmation; failures can have unknown outcome.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `bot_id` (`string`, required): No description.

Example input: `{"bot_id":"<bot_id>"}`

### `airspeedmcp_revoke_share`

Revoke share · Destructive

Revoke a native call share after checking full access to its parent.

In-progress snippets cannot be revoked. Embed links made in the app are not
share links and are not found here. Native storage deletion can precede
the database change, so unexpected errors have an unknown outcome.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `call_id` (`string`, required): No description.
- `share_id` (`string`, required): No description.

Example input: `{"call_id":"<call_id>","share_id":"<share_id>"}`

### `airspeedmcp_run_agent`

Run agent · Destructive

Start or continue a one-off Airspeed agent conversation.

This runs an interactive agent, not a scheduled or event-triggered
job. Use list_agent_runs / get_agent_run to find earlier runs and read
their outputs.

Omit thread_id to start a new conversation. Always pass the returned
thread_id on later calls so follow-up questions keep the same
context. Starting again without it creates a new conversation. To
continue an earlier run, pass its list_agent_runs run ID as thread_id.
Use url_link to cite the conversation or send the user to it. When
awaiting_approval is true, send the user to url_link to approve or
deny the change before calling run_agent on this thread again.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `message` (`string`, required): The question or instruction for the agent.
- `thread_id` (`string`, optional): Thread ID returned by a previous run_agent call, or a run
ID from list_agent_runs. Omit to start a new conversation.

Example input: `{"message":"<message>"}`

### `airspeedmcp_save_comment`

Save comment · Destructive

Create or update a native comment; updates require current authorship.

Native notification tasks are scheduled after persistence; success does not
confirm delivery. Creates return the native comment; updates return null.
No cross-record transaction or concurrent-edit guarantee is added.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `data` (`string`, required): No description.

Example input: `{"data":"<data>"}`

### `airspeedmcp_save_task`

Save task · Destructive

Create or patch a task using the app's native task operations.

Create defaults an omitted assignee to you; explicit null is unassigned.
Optional call_id requires current full call access. Updates require the
current tenant and current source-call access, including peer-assigned
tasks on visible calls. Assignee user_id must be in the current tenant.
due_at requires ISO time with an offset; null clears it. completed=true
records completion now, false reopens. Omitted changes remain unchanged.
A successful response acknowledges the native database save. An unknown
outcome must be read back before retrying, especially for creates.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `change` (`string`, required): No description.

Example input: `{"change":"<change>"}`

### `airspeedmcp_set_call_tags`

Set call tags · Destructive

Add or remove one tag on a call you can read in full.

This changes a single tag; it does not replace the call's other tags.
Adding a grouped tag replaces the existing tag in that group. The app's
scorecard follow-ups apply: results whose tag filter no longer matches are
deleted, and scorecards filtered on an added tag are scored in the
background. Scheduled scoring is best-effort and may finish after this
returns. Adding a tag the call already has changes nothing.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `call_id` (`string`, required): No description.
- `operation` (`string`, required): No description. One of: `add`, `remove`.
- `tag_id` (`string`, required): No description.

Example input: `{"call_id":"<call_id>","operation":"add","tag_id":"<tag_id>"}`

### `airspeedmcp_set_comment_reaction`

Set comment reaction · Destructive

Set only your own reaction membership using the native replacement update.

Other users in the read snapshot are retained. Concurrent writes retain the
app's last-write behavior; this does not promise atomic membership updates.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `active` (`boolean`, required): No description.
- `comment_id` (`string`, required): No description.
- `emoji` (`string`, required): No description.

Example input: `{"active":true,"comment_id":"<comment_id>","emoji":"<emoji>"}`

### `airspeedmcp_stop_agent`

Stop agent · Destructive

Request that your conversation's in-flight agent work stop.

Native accepted=true means the stop request was recorded, not that work has
finished stopping. Ownership is required even for administrators.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `thread_id` (`string`, required): No description.

Example input: `{"thread_id":"<thread_id>"}`

### `airspeedmcp_update_call`

Update call · Destructive

Apply one native title or ordinary CRM-deal reassignment.

Requires full call access; native processing and CRM policies still apply.
Pending deal-match choices stay in the app because their replay starts
rubric scoring. Native writes have no new concurrency guarantee.
Follow-ups are best-effort background work; scheduled does not mean complete.
On an unknown outcome inspect current state before retrying.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `call_id` (`string`, required): No description.
- `change` (`string`, required): No description.

Example input: `{"call_id":"<call_id>","change":"<change>"}`

### `airspeedmcp_update_custom_insight`

Update custom insight · Destructive

Change a call or deal custom insight in your organization.

Requires permission to edit custom insights. Pass only the fields to
change; a filter or options set to null is cleared. Switching to a
format without options clears them. A call insight edit applies only to
calls Airspeed processes after it; past calls are not backfilled or
recomputed, so their results keep the previous definition. When
past_answers_may_be_reformatted is true, a daily job may still fit
answers already on past calls to the current format without re-running
the insight. A deal insight edit is recomputed on an open deal over its
full history when the deal next gets a new call, or a new comment at
the next scheduled deal sync, unless it is switched off or paused by the
plan. Always tell the user what the result's user_notice says.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `changes` (`object`, required): Changes to an existing insight. Omitted fields keep their values.

Only a filter or options accepts null, which clears it.
- `insight_id` (`string`, required): No description.

Example input: `{"changes":{},"insight_id":"<insight_id>"}`

### `airspeedmcp_update_deal`

Update deal · Destructive

Apply supported fields through the native authorized CRM writer.

Change amount, close_date (ISO datetime with offset), stage_id,
forecast_category, or configured extra_crm_fields. Omitted fields stay
unchanged; null does not clear. Native validation rejects amount=0 alone.
Stages resolve from current metadata; extra fields retain native writable
field checks. CRM record read/edit checks run as the caller. Success confirms
the native write returned; cache/history remain native best-effort effects.
Follow-ups are scheduled, not confirmed complete. Use get_deal for readback;
do not automatically retry an error whose outcome is unknown.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `changes` (`object`, required): Supported native updates; omission keeps a field unchanged.
- `crm_deal_id` (`string`, required): No description.

Example input: `{"changes":{},"crm_deal_id":"<crm_deal_id>"}`

### `airspeedmcp_update_forecast_quotas`

Update forecast quotas · Destructive

Update forecast quotas with the web app's organization-settings permission.

Supply a user_id, nonnegative forecast_quota, and optional forecast period
for each update. A period also saves a quota for that specific period;
every update sets the user's current quota. Null quota values are skipped.
Returns only updated users in your organization; unknown IDs and users
outside your organization are skipped. Requires permission to edit
organization settings, which administrators hold by default.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `quota_updates` (`array`, required): No description.

Example input: `{"quota_updates":[]}`

## Related

Other CRM & Sales connectors ([all 174](/agentkit/connectors/?category=crm-sales)):

- [Salesforce](/agentkit/connectors/salesforce/): Scalekit connector, OAuth, 74 tools
- [HubSpot](/agentkit/connectors/hubspot/): Scalekit connector, OAuth, 457 tools
- [Close](/agentkit/connectors/close/): Scalekit connector, OAuth, 103 tools


---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |
