> **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 Agenty

The Agenty connector lets your AI agent act in each user's Agenty account. Each user connects their own Agenty access token once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 57 tools.

**Authentication:** Bearer Token
**Categories:** Automation, Analytics
**Tools:** 57: 21 read, 24 write, 12 destructive
**Users sign in with:** Access token
**Built by:** Scalekit connector
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=AGENTY)

## 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 Agenty connection

   In **AgentKit > Connections**, create an Agenty connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

4. ### 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 = 'agenty'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Agenty:', 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: 'agenty_agents_list',
     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 = "agenty"
   identifier = "user_123"

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

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

   ```bash
   python quickstart.py
   ```

   Each user opens the link once and enters their Agenty credentials there. 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: 'agenty_agent_get',
  toolInput: {
    agent_id: '<agent_id>',
  },
  connector: 'agenty',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="agenty_agent_get",
    tool_input={
        "agent_id": "<agent_id>",
    },
    connection_name="agenty",
    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.

### `agenty_agent_get`

Get Agent · Read-only

Get one agent's full configuration. Returns name, type, description, tags, start URL, collections and fields with their selectors, browser and proxy settings, and scripts. Use this before changing an agent with agenty_agent_update.

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

Inputs:

- `agent_id` (`string`, required): ID of the agent. Find it with agenty_agents_list. Example: abcd123456.

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

### `agenty_agent_input_get`

Get Agent Input · Read-only

Get the input of an agent: the URLs or data it processes, or the list or agent it reads them from. Returns the input type and data. Use this before changing the input.

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

Inputs:

- `agent_id` (`string`, required): ID of the agent. Find it with agenty_agents_list. Example: abcd123456.

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

### `agenty_agent_result_get`

Get Agent Latest Result · Read-only

Get the latest scraped data of an agent as JSON, with paging, sorting and search, optionally for one collection. Returns the rows with their fields and the total count. Use this to read an agent's most recent data without looking up the job.

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

Inputs:

- `agent_id` (`string`, required): ID of the agent. Find it with agenty_agents_list. Example: abcd123456.
- `collection` (`integer`, optional): Index of the collection to return when the agent has several (0 is the first). Example: 0.
- `limit` (`integer`, optional): Maximum number of rows to return. Example: 25.
- `offset` (`integer`, optional): Number of rows to skip, for paging. Example: 0.
- `order` (`string`, optional): Sort order: asc or desc. Example: desc. One of: `asc`, `desc`.
- `search` (`string`, optional): Text to search for. Example: product.
- `sort` (`string`, optional): Field to sort by, e.g. created_at. Example: created_at.

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

### `agenty_agent_schedule_get`

Get Agent Schedule · Read-only

Get the schedule of an agent. Returns the cron expression, description and whether it is enabled. Use this before changing the schedule.

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

Inputs:

- `agent_id` (`string`, required): ID of the agent. Find it with agenty_agents_list. Example: abcd123456.

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

### `agenty_agents_list`

List Agents · Read-only

List the web scraping, crawling and change detection agents in your Agenty account, with paging, sorting and search. Returns per agent its ID, name, type, description, tags, project and dates. Use this to find an agent. Use agenty_agent_get for one agent's full configuration.

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

Inputs:

- `limit` (`integer`, optional): Maximum number of agents to return. Example: 25.
- `offset` (`integer`, optional): Number of agents to skip, for paging. Example: 0.
- `order` (`string`, optional): Sort order: asc or desc. Example: desc. One of: `asc`, `desc`.
- `search` (`string`, optional): Text to search for. Example: product.
- `sort` (`string`, optional): Field to sort by, e.g. created_at. Example: created_at.

Example input: `{}`

### `agenty_connections_list`

List Connections · Read-only

List the third-party connections (Google Sheets, Dropbox, S3, Shopify and so on) that workflows can send data to. Returns per connection its ID, name, type and status.

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

Inputs: none.

Example input: `{}`

### `agenty_job_get`

Get Job · Read-only

Get the status and details of one job. Returns status (queued, started, completed, stopped, failed), pages processed and failed, credits used and timings. Use this to follow a job from agenty_job_start.

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

Inputs:

- `job_id` (`integer`, required): ID of the job (one agent run). Find it with agenty_jobs_list. Example: 1234567.

Example input: `{"job_id":1234567}`

### `agenty_job_logs_list`

List Job Logs · Read-only

List the execution log lines of a job, with paging and search. Returns timestamps, levels and messages. Use this to debug a failed or partial job.

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

Inputs:

- `job_id` (`integer`, required): ID of the job (one agent run). Find it with agenty_jobs_list. Example: 1234567.
- `limit` (`integer`, optional): Maximum number of log lines to return. Example: 25.
- `offset` (`integer`, optional): Number of log lines to skip, for paging. Example: 0.
- `order` (`string`, optional): Sort order: asc or desc. Example: desc. One of: `asc`, `desc`.
- `search` (`string`, optional): Text to search for. Example: product.
- `sort` (`string`, optional): Field to sort by, e.g. created_at. Example: created_at.

Example input: `{"job_id":1234567}`

### `agenty_job_result_get`

Get Job Result · Read-only

Get the scraped data of a job as JSON, with paging, sorting and search, optionally for one collection. Returns the rows with their fields and the total count. Use this to read a specific run's data. Use agenty_agent_result_get for an agent's latest data.

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

Inputs:

- `job_id` (`integer`, required): ID of the job (one agent run). Find it with agenty_jobs_list. Example: 1234567.
- `collection` (`integer`, optional): Index of the collection to return when the agent has several (0 is the first). Example: 0.
- `limit` (`integer`, optional): Maximum number of rows to return. Example: 25.
- `offset` (`integer`, optional): Number of rows to skip, for paging. Example: 0.
- `order` (`string`, optional): Sort order: asc or desc. Example: desc. One of: `asc`, `desc`.
- `search` (`string`, optional): Text to search for. Example: product.
- `sort` (`string`, optional): Field to sort by, e.g. created_at. Example: created_at.

Example input: `{"job_id":1234567}`

### `agenty_jobs_list`

List Jobs · Read-only

List agent jobs (runs), optionally for one agent, with paging, sorting and search. Returns per job its ID, agent, status, pages processed, credits and start and end times. Use this to see recent runs. Use agenty_job_get for one job.

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

Inputs:

- `agent_id` (`string`, optional): Only jobs of this agent. Example: abcd123456.
- `limit` (`integer`, optional): Maximum number of jobs to return. Example: 25.
- `offset` (`integer`, optional): Number of jobs to skip, for paging. Example: 0.
- `order` (`string`, optional): Sort order: asc or desc. Example: desc. One of: `asc`, `desc`.
- `search` (`string`, optional): Text to search for. Example: product.
- `sort` (`string`, optional): Field to sort by, e.g. created_at. Example: created_at.

Example input: `{}`

### `agenty_list_get`

Get List · Read-only

Get one List with its name, description, columns and row count. Use agenty_list_rows_list for its rows.

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

Inputs:

- `list_id` (`integer`, required): ID of the list. Find it with agenty_lists_list. Example: 4567.

Example input: `{"list_id":4567}`

### `agenty_list_row_get`

Get List Row · Read-only

Get one row of a List. Returns its ID and column values.

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

Inputs:

- `list_id` (`integer`, required): ID of the list. Find it with agenty_lists_list. Example: 4567.
- `row_id` (`string`, required): ID of the list row, from agenty_list_rows_list. Example: 65a1b2c3d4e5f60718293a4b.

Example input: `{"list_id":4567,"row_id":"<row_id>"}`

### `agenty_list_rows_list`

List List Rows · Read-only

Get the rows of a List, with paging, sorting and search. Returns rows with their ID and column values. Use this to read a List's data.

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

Inputs:

- `list_id` (`integer`, required): ID of the list. Find it with agenty_lists_list. Example: 4567.
- `limit` (`integer`, optional): Maximum number of rows to return. Example: 25.
- `offset` (`integer`, optional): Number of rows to skip, for paging. Example: 0.
- `order` (`string`, optional): Sort order: asc or desc. Example: desc. One of: `asc`, `desc`.
- `search` (`string`, optional): Text to search for. Example: product.
- `sort` (`string`, optional): Field to sort by, e.g. created_at. Example: created_at.

Example input: `{"list_id":4567}`

### `agenty_lists_list`

List Lists · Read-only

List the Lists in your account (tables of URLs or input data for agents), with paging, sorting and search. Returns per List its ID, name, description, row count and dates. Use this to find a List.

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

Inputs:

- `limit` (`integer`, optional): Maximum number of lists to return. Example: 25.
- `offset` (`integer`, optional): Number of lists to skip, for paging. Example: 0.
- `order` (`string`, optional): Sort order: asc or desc. Example: desc. One of: `asc`, `desc`.
- `search` (`string`, optional): Text to search for. Example: product.
- `sort` (`string`, optional): Field to sort by, e.g. created_at. Example: created_at.

Example input: `{}`

### `agenty_project_get`

Get Project · Read-only

Get one project with its agents. Returns the name, description and agent list.

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

Inputs:

- `id` (`integer`, required): ID of the project. Find it with agenty_projects_list. Example: 321.

Example input: `{"id":321}`

### `agenty_projects_list`

List Projects · Read-only

List the projects that group agents, with paging, sorting and search. Returns per project its ID, name, description and agent count. Use this to find a project.

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

Inputs:

- `limit` (`integer`, optional): Maximum number of projects to return. Example: 25.
- `offset` (`integer`, optional): Number of projects to skip, for paging. Example: 0.
- `order` (`string`, optional): Sort order: asc or desc. Example: desc. One of: `asc`, `desc`.
- `search` (`string`, optional): Text to search for. Example: product.
- `sort` (`string`, optional): Field to sort by, e.g. created_at. Example: created_at.

Example input: `{}`

### `agenty_usage_get`

Get Usage Report · Read-only

Get account usage reports: pages scraped by agent and by date, and credits used, for a date range (default the last 30 days). Returns the usage series and totals. Use this to watch credit consumption.

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

Inputs:

- `end` (`string`, optional): End date (YYYY-MM-DD); defaults to today. Example: 2026-06-30.
- `start` (`string`, optional): Start date (YYYY-MM-DD); defaults to 30 days ago. Example: 2026-06-01.

Example input: `{}`

### `agenty_user_get`

Get Team Member · Read-only

Get one team member. Returns name, email, role and status.

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

Inputs:

- `user_id` (`integer`, required): ID of the team member. Find it with agenty_users_list. Example: 2001.

Example input: `{"user_id":2001}`

### `agenty_users_list`

List Team Members · Read-only

List the team members of your Agenty account, with paging, sorting and search. Returns per member the ID, name, email, role and status.

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

Inputs:

- `limit` (`integer`, optional): Maximum number of team members to return. Example: 25.
- `offset` (`integer`, optional): Number of team members to skip, for paging. Example: 0.
- `order` (`string`, optional): Sort order: asc or desc. Example: desc. One of: `asc`, `desc`.
- `search` (`string`, optional): Text to search for. Example: product.
- `sort` (`string`, optional): Field to sort by, e.g. created_at. Example: created_at.

Example input: `{}`

### `agenty_workflow_get`

Get Workflow · Read-only

Get one workflow. Returns its name, agents, trigger, actions and enabled flag.

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

Inputs:

- `id` (`integer`, required): ID of the workflow. Find it with agenty_workflows_list. Example: 891.

Example input: `{"id":891}`

### `agenty_workflows_list`

List Workflows · Read-only

List the workflows that run actions (webhooks, emails, uploads) after agent jobs. Returns per workflow its ID, name, agents, trigger, actions and enabled flag. Use this to see integrations.

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

Inputs: none.

Example input: `{}`

### `agenty_agent_copy`

Copy Agent · Write

Clone an agent with a new name, keeping its configuration. Returns the new agent. Use this to make a variant of a working agent.

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

Inputs:

- `agent_id` (`string`, required): ID of the agent. Find it with agenty_agents_list. Example: abcd123456.
- `name` (`string`, required): Name of the copy. Example: sk-test Product scraper (copy)

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

### `agenty_agent_create`

Create Agent · Write

Create a web scraping, crawling or change detection agent from a start URL and CSS, XPath or regex field selectors, and optionally run it right away (start=1). Returns the new agent with its ID. Use agenty_agent_patch to add a description or tags, agenty_job_start to run it later and agenty_job_result_get to read data.

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

Inputs:

- `config` (`object`, required): Agent configuration: the start url and the collections to extract, each with a name and fields (name, type CSS/XPATH/REGEX, selector and what to extract such as TEXT, HTML or an ATTR). Example shape: {"url": ..., "collections": [{"name": ..., "fields": [...]}]}. Example: {"url":"https://example.com","collections":[{"name":"Products","fields":[{"name":"title","type":"CSS","selector":"h1","extract":"TEXT"},{"name":"price","type...
- `name` (`string`, required): Agent name. Example: sk-test Product scraper.
- `type` (`string`, required): Agent type: scraping, crawling or changedetection. Example: scraping. One of: `scraping`, `crawling`, `changedetection`.
- `start` (`integer`, optional): Set to 1 to start a job right after the agent is created. Example: 1.

Example input: `{"config":{},"name":"<name>","type":"scraping"}`

### `agenty_agent_input_set`

Set Agent Input · Write

Set what an agent processes: a manual list of URLs or values, a List, or another agent's output. Returns the updated input. Use agenty_job_start afterwards to run the agent on it.

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

Inputs:

- `agent_id` (`string`, required): ID of the agent. Find it with agenty_agents_list. Example: abcd123456.
- `data` (`array`, required): Input values: URLs or text for manual input, or a single List or agent ID. Example: ["https://example.com/page-1","https://example.com/page-2"]
- `type` (`string`, required): Input source: manual (URLs in data), list (a List ID in data) or agent (another agent's ID in data). Example: manual. One of: `manual`, `list`, `agent`.

Example input: `{"agent_id":"<agent_id>","data":["https://example.com/page-1","https://example.com/page-2"],"type":"manual"}`

### `agenty_agent_patch`

Update Agent Details · Write

Change an agent's name, description or tags without touching its configuration. Returns the updated agent. Use agenty_agent_update to change selectors or the start URL.

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

Inputs:

- `agent_id` (`string`, required): ID of the agent. Find it with agenty_agents_list. Example: abcd123456.
- `description` (`string`, optional): New description. Example: Scrape product title, price and stock.
- `name` (`string`, optional): New agent name. Example: sk-test Product scraper v2.
- `tags` (`array`, optional): New tags; replaces the existing tags. Example: ["ecommerce","daily"]

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

### `agenty_agent_schedule_set`

Set Agent Schedule · Write

Schedule an agent to run automatically with a cron expression; each scheduled run uses credits. Returns the schedule. Use agenty_agent_schedule_toggle to pause it.

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

Inputs:

- `agent_id` (`string`, required): ID of the agent. Find it with agenty_agents_list. Example: abcd123456.
- `expression` (`string`, required): Cron expression (minute hour day month weekday), in UTC. Example: 0 9 * * *.
- `type` (`string`, required): Schedule type; cron is supported. Example: cron. One of: `cron`.
- `description` (`string`, optional): Human-readable description of the schedule. Example: Every day at 9 AM.

Example input: `{"agent_id":"<agent_id>","expression":"<expression>","type":"cron"}`

### `agenty_agent_schedule_toggle`

Enable or Disable Agent Schedule · Write

Turn an agent's schedule on or off without deleting it. Returns the updated schedule.

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

Inputs:

- `agent_id` (`string`, required): ID of the agent. Find it with agenty_agents_list. Example: abcd123456.
- `is_enabled` (`boolean`, required): true to enable the schedule, false to pause it. Example: false.

Example input: `{"agent_id":"<agent_id>","is_enabled":true}`

### `agenty_agent_scripts_update`

Update Agent Scripts · Write

Set the JavaScript pre-processing and post-processing scripts of an agent, and turn each on or off. Returns the updated agent. Use the post script to clean or reshape scraped data.

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

Inputs:

- `agent_id` (`string`, required): ID of the agent. Find it with agenty_agents_list. Example: abcd123456.
- `post` (`object`, optional): Post-processing script: is_enabled and code (JavaScript that receives data and returns it). Example: {"is_enabled":true,"code":"return data;"}
- `pre` (`object`, optional): Pre-processing script: is_enabled and code (JavaScript run before scraping each page). Example: {"is_enabled":false}

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

### `agenty_agent_transfer`

Transfer Agent · Write

Transfer an agent to another Agenty account, identified by the account email. The agent leaves your account. Returns a success message. Use agenty_agent_copy to keep a copy first.

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

Inputs:

- `agent_id` (`string`, required): ID of the agent. Find it with agenty_agents_list. Example: abcd123456.
- `email` (`string`, required): Email address of the Agenty account to receive the agent. Example: user@example.com.

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

### `agenty_agent_update`

Replace Agent Configuration · Write

Replace an agent's configuration (name, type and the full config with URL, collections and fields). Returns the updated agent. Use agenty_agent_patch to change only the name, description or tags.

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

Inputs:

- `agent_id` (`string`, required): ID of the agent. Find it with agenty_agents_list. Example: abcd123456.
- `config` (`object`, required): Agent configuration: the start url and the collections to extract, each with a name and fields (name, type CSS/XPATH/REGEX, selector and what to extract such as TEXT, HTML or an ATTR). Example shape: {"url": ..., "collections": [{"name": ..., "fields": [...]}]}. Example: {"url":"https://example.com","collections":[{"name":"Products","fields":[{"name":"title","type":"CSS","selector":"h1","extract":"TEXT"},{"name":"price","type...
- `name` (`string`, required): Agent name. Example: sk-test Product scraper.
- `type` (`string`, required): Agent type: scraping, crawling or changedetection. Example: scraping. One of: `scraping`, `crawling`, `changedetection`.

Example input: `{"agent_id":"<agent_id>","config":{},"name":"<name>","type":"scraping"}`

### `agenty_connection_rename`

Rename Connection · Write

Rename a third-party connection. Returns the updated connection.

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

Inputs:

- `id` (`integer`, required): ID of the connection. Find it with agenty_connections_list. Example: 77.
- `name` (`string`, required): New connection name. Example: My Google Sheets.

Example input: `{"id":77,"name":"<name>"}`

### `agenty_job_start`

Start Job · Write

Run an agent in the Agenty cloud now; uses page credits. Returns the new job ID. Use agenty_job_get to follow it and agenty_job_result_get to read the data.

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

Inputs:

- `agent_id` (`string`, required): ID of the agent to run. Example: abcd123456.

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

### `agenty_job_stop`

Stop Job · Write

Stop a running job. Returns the updated job status. Use this to cancel a long or mistaken run.

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

Inputs:

- `job_id` (`integer`, required): ID of the job (one agent run). Find it with agenty_jobs_list. Example: 1234567.

Example input: `{"job_id":1234567}`

### `agenty_list_create`

Create List · Write

Create a List to hold URLs or other input data for agents. Returns the new List with its ID. Use agenty_list_rows_add to fill it.

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

Inputs:

- `name` (`string`, required): List name. Example: sk-test Product URLs.
- `description` (`string`, optional): What the List holds. Example: Product URLs to scrape.

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

### `agenty_list_row_update`

Update List Row · Write

Replace the column values of one List row. Returns the updated row.

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

Inputs:

- `list_id` (`integer`, required): ID of the list. Find it with agenty_lists_list. Example: 4567.
- `row_id` (`string`, required): ID of the list row, from agenty_list_rows_list. Example: 65a1b2c3d4e5f60718293a4b.
- `values` (`object`, required): New column values of the row, e.g. {"url": "https://example.com/page-3"}. Example: {"url":"https://example.com/page-3"}

Example input: `{"list_id":4567,"row_id":"<row_id>","values":{"url":"https://example.com/page-3"}}`

### `agenty_list_rows_add`

Add List Rows · Write

Append rows to a List; each row is an object of column values such as {"url": ...}. Returns the added rows. Use agenty_list_row_update to change a row.

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

Inputs:

- `list_id` (`integer`, required): ID of the list. Find it with agenty_lists_list. Example: 4567.
- `rows` (`array`, required): Rows to append, each an object of column values. Example: [{"url":"https://example.com/page-1"},{"url":"https://example.com/page-2"}]

Example input: `{"list_id":4567,"rows":[{"url":"https://example.com/page-1"},{"url":"https://example.com/page-2"}]}`

### `agenty_list_update`

Update List · Write

Rename a List or change its description. Returns the updated List.

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

Inputs:

- `list_id` (`integer`, required): ID of the list. Find it with agenty_lists_list. Example: 4567.
- `name` (`string`, required): List name. Example: sk-test Product URLs v2.
- `description` (`string`, optional): What the List holds. Example: Product URLs to scrape daily.

Example input: `{"list_id":4567,"name":"<name>"}`

### `agenty_project_agents_add`

Add Agents to Project · Write

Add one or more agents to a project. Returns the updated project. Use agenty_project_agent_remove to take one out.

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

Inputs:

- `agent_ids` (`array`, required): IDs of the agents to add. Example: ["abcd123456","efgh789012"]
- `id` (`integer`, required): ID of the project. Find it with agenty_projects_list. Example: 321.

Example input: `{"agent_ids":["abcd123456","efgh789012"],"id":321}`

### `agenty_project_create`

Create Project · Write

Create a project to group related agents. Returns the new project. Use agenty_project_agents_add to put agents in it.

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

Inputs:

- `name` (`string`, required): Project name. Example: sk-test Ecommerce.
- `description` (`string`, optional): Project description. Example: Agents for ecommerce websites.

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

### `agenty_project_update`

Update Project · Write

Rename a project or change its description. Returns the updated project.

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

Inputs:

- `id` (`integer`, required): ID of the project. Find it with agenty_projects_list. Example: 321.
- `name` (`string`, required): Project name. Example: sk-test Ecommerce.
- `description` (`string`, optional): Project description. Example: Agents for ecommerce websites.

Example input: `{"id":321,"name":"<name>"}`

### `agenty_user_invite`

Invite Team Member · Write

Invite a person to your Agenty account with a role; Agenty emails them. Returns the new team member. Use agenty_user_update to change the role later.

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

Inputs:

- `email` (`string`, required): Team member's email address. Example: jane@example.com.
- `name` (`string`, required): Team member's name. Example: Jane Doe.
- `role` (`string`, required): Role in the account, e.g. Manager or Viewer. Example: Manager.
- `status` (`string`, optional): Account status: active or inactive. Example: active. One of: `active`, `inactive`.

Example input: `{"email":"<email>","name":"<name>","role":"<role>"}`

### `agenty_user_update`

Update Team Member · Write

Change a team member's name, email, role or status. Returns the updated member. Set status to inactive to suspend access.

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

Inputs:

- `email` (`string`, required): Team member's email address. Example: jane@example.com.
- `name` (`string`, required): Team member's name. Example: Jane Doe.
- `role` (`string`, required): Role in the account, e.g. Manager or Viewer. Example: Manager.
- `user_id` (`integer`, required): ID of the team member. Find it with agenty_users_list. Example: 2001.
- `status` (`string`, optional): Account status: active or inactive. Example: active. One of: `active`, `inactive`.

Example input: `{"email":"<email>","name":"<name>","role":"<role>","user_id":2001}`

### `agenty_workflow_create`

Create Workflow · Write

Create a workflow that sends scraped data to a webhook, email, Google Sheets, S3 or another destination when agent jobs complete or fail. Returns the new workflow. Use agenty_workflow_toggle to pause it.

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

Inputs:

- `actions` (`array`, required): Actions to run, each with a type (webhook, email, google_sheets, s3, dropbox...) and its config. Example: [{"type":"webhook","config":{"url":"https://example.com/webhook"}}]
- `agents` (`object`, required): Which agents trigger the workflow: {"all": true} or {"ids": [agent IDs]}. Example: {"all":true}
- `name` (`string`, required): Workflow name. Example: sk-test Webhook on completion.
- `trigger` (`object`, required): When it runs: {"when": [events]}, with events such as job_completed or job_failed. Example: {"when":["job_completed"]}

Example input: `{"actions":[{"type":"webhook","config":{"url":"https://example.com/webhook"}}],"agents":{"all":true},"name":"<name>","trigger":{"when":["job_completed"]}}`

### `agenty_workflow_toggle`

Enable or Disable Workflow · Write

Turn a workflow on or off. Returns the updated workflow.

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

Inputs:

- `id` (`integer`, required): ID of the workflow. Find it with agenty_workflows_list. Example: 891.
- `is_enabled` (`boolean`, required): true to enable the workflow, false to pause it. Example: false.

Example input: `{"id":891,"is_enabled":true}`

### `agenty_workflow_update`

Update Workflow · Write

Replace a workflow's name, agents, trigger and actions. Returns the updated workflow.

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

Inputs:

- `actions` (`array`, required): Actions to run, each with a type (webhook, email, google_sheets, s3, dropbox...) and its config. Example: [{"type":"webhook","config":{"url":"https://example.com/webhook"}}]
- `agents` (`object`, required): Which agents trigger the workflow: {"all": true} or {"ids": [agent IDs]}. Example: {"all":true}
- `id` (`integer`, required): ID of the workflow. Find it with agenty_workflows_list. Example: 891.
- `name` (`string`, required): Workflow name. Example: sk-test Webhook on completion.
- `trigger` (`object`, required): When it runs: {"when": [events]}, with events such as job_completed or job_failed. Example: {"when":["job_completed"]}

Example input: `{"actions":[{"type":"webhook","config":{"url":"https://example.com/webhook"}}],"agents":{"all":true},"id":891,"name":"<name>","trigger":{"when":["job_completed"]}}`

### `agenty_agent_delete`

Delete Agent · Destructive

Delete one agent with its jobs and results. Returns a success message. Use agenty_agents_delete to delete several at once.

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

Inputs:

- `agent_id` (`string`, required): ID of the agent. Find it with agenty_agents_list. Example: abcd123456.

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

### `agenty_agent_schedule_delete`

Delete Agent Schedule · Destructive

Remove the schedule of an agent. Returns a success message. Use agenty_agent_schedule_toggle to pause it instead.

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

Inputs:

- `agent_id` (`string`, required): ID of the agent. Find it with agenty_agents_list. Example: abcd123456.

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

### `agenty_agents_delete`

Delete Agents · Destructive

Delete several agents at once by ID. Returns a success message. Use agenty_agent_delete for one agent.

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

Inputs:

- `agent_id` (`array`, required): IDs of the agents to delete. Example: ["abcd123456","efgh789012"]

Example input: `{"agent_id":["abcd123456","efgh789012"]}`

### `agenty_connection_delete`

Delete Connection · Destructive

Delete a third-party connection; workflows that use it stop delivering there. Returns a success message.

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

Inputs:

- `id` (`integer`, required): ID of the connection. Find it with agenty_connections_list. Example: 77.

Example input: `{"id":77}`

### `agenty_list_delete`

Delete List · Destructive

Delete a List and all its rows. Returns a success message. Use agenty_list_rows_clear to empty it but keep it.

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

Inputs:

- `list_id` (`integer`, required): ID of the list. Example: 4567.

Example input: `{"list_id":4567}`

### `agenty_list_row_delete`

Delete List Row · Destructive

Delete one row of a List. Returns a success message. Use agenty_list_rows_delete for several rows.

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

Inputs:

- `list_id` (`integer`, required): ID of the list. Find it with agenty_lists_list. Example: 4567.
- `row_id` (`string`, required): ID of the list row, from agenty_list_rows_list. Example: 65a1b2c3d4e5f60718293a4b.

Example input: `{"list_id":4567,"row_id":"<row_id>"}`

### `agenty_list_rows_clear`

Clear List · Destructive

Remove every row from a List, keeping the List itself. Returns a success message. Use agenty_list_delete to delete the List too.

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

Inputs:

- `list_id` (`integer`, required): ID of the list. Find it with agenty_lists_list. Example: 4567.

Example input: `{"list_id":4567}`

### `agenty_list_rows_delete`

Delete List Rows · Destructive

Delete several rows of a List by ID. Returns a success message. Use agenty_list_rows_clear to delete every row.

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

Inputs:

- `id` (`string`, required): Comma-separated IDs of the rows to delete. Example: 65a1b2c3d4e5f60718293a4b,65a1b2c3d4e5f60718293a4c.
- `list_id` (`integer`, required): ID of the list. Find it with agenty_lists_list. Example: 4567.

Example input: `{"id":"<id>","list_id":4567}`

### `agenty_project_agent_remove`

Remove Agent from Project · Destructive

Remove one agent from a project; the agent itself is kept. Returns a success message.

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

Inputs:

- `agent_id` (`string`, required): ID of the agent to remove from the project. Example: abcd123456.
- `id` (`integer`, required): ID of the project. Find it with agenty_projects_list. Example: 321.

Example input: `{"agent_id":"<agent_id>","id":321}`

### `agenty_projects_delete`

Delete Projects · Destructive

Delete one or more projects by ID; their agents are kept. Returns a success message.

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

Inputs:

- `project_id` (`array`, required): IDs of the projects to delete. Example: ["321"]

Example input: `{"project_id":["321"]}`

### `agenty_users_remove`

Remove Team Members · Destructive

Remove one or more team members from your account by ID. Returns a success message.

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

Inputs:

- `user_id` (`array`, required): IDs of the team members to remove. Example: ["2001"]

Example input: `{"user_id":["2001"]}`

### `agenty_workflow_delete`

Delete Workflow · Destructive

Delete a workflow. Returns a success message. Use agenty_workflow_toggle to pause it instead.

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

Inputs:

- `id` (`integer`, required): ID of the workflow. Find it with agenty_workflows_list. Example: 891.

Example input: `{"id":891}`

## Related

Other Automation connectors ([all 91](/agentkit/connectors/?category=automation)):

- [Mailchimp](/agentkit/connectors/mailchimp/): Scalekit connector, OAuth, 73 tools
- [Twilio](/agentkit/connectors/twilio/): Scalekit connector, Username and password, 61 tools
- [Stripe](/agentkit/connectors/stripe/): Scalekit connector, Access token, 178 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 |
