> **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 Vibe MCP server

The Vibe MCP connector routes your AI agent's tool calls to Vibe's own MCP server through Scalekit. Each user signs in to Vibe once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 24 tools.

**Authentication:** OAuth 2.1/DCR
**Categories:** Marketing
**Tools:** 24: 20 read, 0 write, 4 destructive
**Users sign in with:** OAuth
**OAuth app:** Your own Vibe MCP server app
**Built by:** Vendor MCP
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=VIBEMCP)

## 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 Vibe MCP connection

   In **AgentKit > Connections**, create a Vibe 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

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

   Then enter the app's Client ID and Client Secret on the Vibe 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 = 'vibemcp'
   const identifier = 'user_123'

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

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

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="vibemcp_list_advertisers",
       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: 'vibemcp_get_activity_log',
  toolInput: {
    models: [],
  },
  connector: 'vibemcp',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="vibemcp_get_activity_log",
    tool_input={
        "models": [],
    },
    connection_name="vibemcp",
    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.

### `vibemcp_get_activity_log`

Get Activity Log · Read-only

Returns the change history (who changed what, and when) for the given records. You only have access to change history from 2026-05-21 onward.

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

Inputs:

- `models` (`array`, required): The entity types whose change history to fetch. By default the change history of each selected model's nested sub-records are included too; see `includeNestedRecords`.
- `actions` (`string`, optional): Narrow to only creations and/or deletions of records (e.g. creatives added to or removed from a campaign). Omit to include all changes, including field updates.
- `from` (`string`, optional): Filter changes on or after this date (inclusive), format "YYYY-MM-DD".
- `includeNestedRecords` (`boolean`, optional): Whether to also include changes to records nested under the selected models (e.g. CAMPAIGN also returns changes to its strategies, their creatives and targeting audiences, and its experiments). Keep the default (true): most edits to an entity are actually made on its nested records, so leaving them out will miss real changes. Only set false when the user explicitly wants changes to the named entity itself, excluding its children. Default: `true`.
- `limit` (`string`, optional): Max number of changes to return, most recent first. Default: `25`.
- `scopes` (`string`, optional): Restrict results to records tied to these entities. Selected models unrelated to every listed entity are excluded. Omit to return history for ALL records of the selected models.
- `sources` (`string`, optional): Filter by one or more sources that made the change: APP (a user in the Vibe web app), AGENT (the in-app Vibe AI agent), PUBLIC_API (an external caller via the public API), MCP (an external AI agent or automation via the MCP), SYSTEM (an automated Vibe action with no human involved).
- `to` (`string`, optional): Filter changes on or before this date (inclusive), format "YYYY-MM-DD".

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

### `vibemcp_get_advertiser_details`

Get Advertiser · Read-only

Get detailed advertiser information including website URL, industry, apps, and campaign count. Use this when the user asks about a specific advertiser beyond just its name. Returns an error if the advertiser ID does not exist or the caller lacks access.

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

Inputs:

- `advertiserId` (`string`, required): The advertiser ID to look up

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

### `vibemcp_get_business_rules`

Get Business Rules · Read-only

Load platform documentation for a knowledge domain. Call when Vibe-specific rules or best practices apply to what you are about to do or explain.

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

Inputs:

- `domain` (`string`, required): The knowledge domain to retrieve:
Use `getting_started` for Platform basics, account setup, and FAQ.
Use `campaign_setup` for Campaign configuration, goals, targeting, creatives, and prerequisites.
Use `pixel_tracking_reporting` for Pixel setup, conversion tracking, and reporting.
Use `integrations` for Shopify, Google Analytics, Klaviyo, HubSpot, and other platform integrations.
Use `billing_support` for Billing, payments, account management, and support topics.
Use `campaign_optimization_playbook` for Optimization strategies, budget allocation, pacing, and performance best practices.
Use `awareness_playbook` for Brand awareness, reach, frequency, and ad recall best practices. One of: `getting_started`, `campaign_setup`, `pixel_tracking_reporting`, `integrations`, `billing_support`, `campaign_optimization_playbook`, `awareness_playbook`.

Example input: `{"domain":"getting_started"}`

### `vibemcp_get_campaign_details`

Get Campaign · Read-only

Get campaign metadata including name, status, start/end dates, budget, and goal. Use this when the user asks about a specific campaign. Returns an error if the campaign ID does not exist or the caller lacks access. Includes the link to the campaign summary page on the Vibe dashboard, where the user can modify or publish a campaign.

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

Inputs:

- `campaignId` (`string`, required): The campaign ID to look up

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

### `vibemcp_get_creative_details`

Get Creative · Read-only

Get detailed creative information including approval status, duration, and whether it is used in an active campaign. Use this when the user asks about a specific creative. Returns an error if the creative ID does not exist or the caller lacks access.

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

Inputs:

- `creativeId` (`string`, required): The video creative ID to look up

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

### `vibemcp_get_strategy_details`

Get Strategy · Read-only

Get detailed strategy information including targeting, bidding, and creatives. Use this when the user asks about a specific strategy's configuration or targeting setup. Returns an error if the strategy ID does not exist or the caller lacks access.

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

Inputs:

- `strategyId` (`string`, required): The strategy ID to look up

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

### `vibemcp_list_advertisers`

List Advertisers · Read-only

List advertisers for the current tenant. Use this to find advertiser names and IDs when the user asks about a specific advertiser or when you need to disambiguate.

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

Inputs:

- `search` (`string`, optional): Search by advertiser name. Space-separated keywords return results that match any of them (better for broad searches). Keywords inside double quotes match the exact phrase (better for exact searches). Prefer a single call with multiple keywords over multiple separate tool calls.

Example input: `{}`

### `vibemcp_list_campaigns`

List Campaigns · Read-only

List campaigns for the current tenant with optional filters, the most recently updated first. Each campaign includes a displayStatus showing its current state as seen in the dashboard (e.g., Delivering, Paused, Upcoming, Completed, Draft, Archived, Blocked). Use the state filter for delivery states (DELIVERING, PAUSED, UPCOMING, COMPLETED, etc.). Use campaignStatus for lifecycle stages (DRAFT, PUBLISHED, ARCHIVED). Pass goal when the user mentions or implies a campaign objective (e.g., "lead campaign" → LEADS, "awareness campaign" → AWARENESS). Use publishedAfter/publishedBefore for publication date ranges.

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

Inputs:

- `advertiserId` (`string`, optional): Filter by advertiser ID
- `campaignStatus` (`string`, optional): Filter by lifecycle status (DRAFT, PUBLISHED, ARCHIVED). Use DRAFT when user asks about draft campaigns. Most other user queries should use the state filter instead.
- `goal` (`string`, optional): Filter by campaign goal (e.g. AWARENESS, TRAFFIC, RETARGETING).
- `limit` (`string`, optional): Max results to return. Default: `50`.
- `publishedAfter` (`string`, optional): Filter campaigns published on or after this date in format "YYYY-MM-DD" (e.g. "2025-03-01").
- `publishedBefore` (`string`, optional): Filter campaigns published on or before this date in format "YYYY-MM-DD" (e.g. "2025-03-31").
- `search` (`string`, optional): Search by campaign or advertiser name. Space-separated keywords return results that match any of them (better for broad searches). Keywords inside double quotes match the exact phrase (better for exact searches). Prefer a single call with multiple keywords over multiple separate tool calls.
- `state` (`string`, optional): Filter by delivery state (DELIVERING, PAUSED, UPCOMING, COMPLETED, BLOCKED, etc.). Use when the user asks about delivering, paused, upcoming, or completed campaigns.

Example input: `{}`

### `vibemcp_list_company_list_audiences`

List Company List Audiences · Read-only

List company list audiences for a given advertiser, sorted by most recently created, with their status and size. A company list audience reaches employees of the companies the advertiser uploaded. Use this to find the company list audience IDs to fill `targetingCompanyListAudiences`.

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

Inputs:

- `advertiserId` (`string`, required): The advertiser ID to list company list audiences for.

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

### `vibemcp_list_creatives`

List Creatives · Read-only

List video creatives for the current tenant with optional filters. Use this when the user asks about their creatives, creative status, or wants to see what ads they have.

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

Inputs:

- `advertiserId` (`string`, optional): Filter by advertiser ID
- `label` (`string`, optional): Filter creatives that have at least one label containing the given creative label name.
- `limit` (`string`, optional): Max results to return. Default: `50`.
- `search` (`string`, optional): Search by creative name. Space-separated keywords return results that match any of them (better for broad searches). Keywords inside double quotes match the exact phrase (better for exact searches). Prefer a single call with multiple keywords over multiple separate tool calls.
- `statuses` (`string`, optional): Filter creatives that have one of the given computed creative statuses. Pass all but BLOCKED for creatives usable inside a campaign.

Example input: `{}`

### `vibemcp_list_crm_audiences`

List CRM Audiences · Read-only

List CRM audiences for a given advertiser, sorted by most recently created. Use this to find the CRM audience IDs to fill `targetingCrmAudiences`.

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

Inputs:

- `advertiserId` (`string`, required): The advertiser ID to list CRM audiences for.

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

### `vibemcp_list_firmographic_audiences`

List Firmographic Audiences · Read-only

List firmographic audiences for a given advertiser, sorted by most recently created, with their status and size. A firmographic audience reaches employees of companies matching company and job criteria. Use this to find the firmographic audience IDs to fill `targetingFirmographicAudiences`.

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

Inputs:

- `advertiserId` (`string`, required): The advertiser ID to list firmographic audiences for.

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

### `vibemcp_list_lookalike_audiences`

List Lookalike Audiences · Read-only

List lookalike audiences for a given advertiser, sorted by most recently created, with the seed audiences each one expands from. Use this to find the lookalike audience IDs to fill `targetingLookalikeAudiences`.

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

Inputs:

- `advertiserId` (`string`, required): The advertiser ID to list lookalike audiences for.

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

### `vibemcp_list_public_audiences`

List Public Audiences · Read-only

List public audiences (powered by Walmart) also known as "In-Market & Interests", optionally filtered by a keyword in the name/category path or by audience type. Use the IDs to fill `targetingPublicAudiencesControls` or `targetingPublicAudiencesSuggestions` in strategy targeting. Some Walmart audiences are coming soon: they are hidden from this list until they are available.

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

Inputs:

- `audienceType` (`string`, optional): Only display audiences of this type. `PERSONA`: who a household is (life stage, lifestyle, seasonal moments). `RECENT_BUYERS`: households who have recently purchased within a category. `IN_MARKET`: households with high intent to purchase within a category. `DEMOGRAPHIC`: demographic information about households.
- `limit` (`string`, optional): Max audiences to return. Default: `50`.
- `search` (`string`, optional): Search by name or by its category path. Space-separated keywords return results that match any of them (better for broad searches). Keywords inside double quotes match the exact phrase (better for exact searches). Prefer a single call with multiple keywords over multiple separate tool calls.

Example input: `{}`

### `vibemcp_list_strategies`

List Strategies · Read-only

List strategies for a campaign. Use this when the user asks about strategies in a campaign, or when you need to find strategy IDs.

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

Inputs:

- `campaignId` (`string`, required): The campaign ID to list strategies for

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

### `vibemcp_list_tv_inventory`

List TV Inventory · Read-only

List TV inventory items (apps, channels, sports leagues) from the global catalog, optionally filtered by a name search. Use this to find catalog IDs or names, either for channels or live sports.

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

Inputs:

- `inventoryType` (`string`, required): Which subset of the catalog to list: APPS_AND_CHANNELS for streaming apps and TV channels, LIVE_SPORTS for sports leagues/programs. When selecting a channel for `create_or_update_campaign`, pass `inventoryType` matching the strategy `targetingTvInventoryTypeControl` (APPS_AND_CHANNELS or LIVE_SPORTS) as only one can be selected for a given strategy. One of: `APPS_AND_CHANNELS`, `LIVE_SPORTS`.
- `limit` (`string`, optional): Max results to return. Default: `100`.
- `search` (`string`, optional): Search by inventory item name. Space-separated keywords return results that match any of them (better for broad searches). Keywords inside double quotes match the exact phrase (better for exact searches). Prefer a single call with multiple keywords over multiple separate tool calls.

Example input: `{"inventoryType":"APPS_AND_CHANNELS"}`

### `vibemcp_list_url_matching_audiences`

List URL Matching Audiences · Read-only

List URL matching audiences for a given advertiser, sorted by most recently modified. A URL matching audience targets users by the URLs they visited (data coming from Vibe pixel), and is shown as Web Traffic in the Audience Manager. Use this to fill `targetingUrlMatchingAudienceIdIncludedControls`, `targetingUrlMatchingAudienceIdIncludedSuggestions` and `targetingUrlMatchingAudienceIdExcludedControls`.

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

Inputs:

- `advertiserId` (`string`, required): The advertiser ID to list URL matching audiences for.

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

### `vibemcp_query_metrics`

Query Metrics · Read-only

Query reporting metrics from the data warehouse. Use this to get campaign performance data, spend, impressions, and other metrics. You can group by dimensions (DATE, CAMPAIGN_NAME, STATE, etc.) and filter by advertiser or campaign. If user asks about platform, depending on context it could mean DEVICE_SCREEN_TYPE or INVENTORY_CHANNEL_NAME. The query is already scoped by tenant id, no need to pass it. Use the user-friendly names for the dimensions and metrics, not the capitalized technical names.

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

Inputs:

- `dateRange` (`object`, required): Both start and end are inclusive. For "last N days", exclude today: start = today minus N, end = yesterday.
- `metrics` (`array`, required): Metrics to retrieve.
- `orderBy` (`object`, required): No description.
- `advertiserId` (`string`, optional): No description.
- `attributionWindow` (`string`, optional): No description.
- `campaignId` (`string`, optional): No description.
- `dimensions` (`string`, optional): Dimensions to group by. Omit if you need to return aggregate metrics over the date range.
- `filters` (`string`, optional): No description.
- `limit` (`number`, optional): No description.
- `timeGranularity` (`string`, optional): Time bucketing granularity when grouping by date. Required when the DATE dimension is included. Use DAY for daily trends, WEEK for weekly, MONTH for monthly, QUARTER for quarterly, YEAR for annual. Defaults to DAY if omitted with DATE dimension.

Example input: `{"dateRange":{},"metrics":[],"orderBy":{}}`

### `vibemcp_search_help_center`

Search Help Center · Read-only

Answer a general knowledge question from the live Vibe Help Center: how something works, what a term means, or what the policy is.

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

Inputs:

- `question` (`string`, required): The question to answer, self-contained, with pronouns and references resolved.
- `searchPhrase` (`string`, required): Keyword search phrase that will return the top articles matching: 2-6 words of Vibe product vocabulary, not the user's sentence. Matching is keyword-based, so the words must appear in the article.

Example input: `{"question":"<question>","searchPhrase":"<searchPhrase>"}`

### `vibemcp_search_locations`

Search Locations · Read-only

Search for geographic locations by name. Returns matching states, cities, metro areas, counties, or congressional districts with the exact code to use in query_metrics filters, and with the exact ID to use in strategy targeting controls. Use this when the user mentions a geographic location and you need the correct filter value.

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

Inputs:

- `input` (`string`, required): Geographic name to search for. Space-separated keywords return results that match any of them (better for broad searches). Keywords inside double quotes match the exact phrase (better for exact searches). Prefer a single call with multiple keywords over multiple separate tool calls. Acronyms match multi-word names by word initials (e.g. 'nc' matches 'North Carolina').
- `limit` (`string`, optional): Max results to return. Default: `100`.
- `location_types` (`string`, optional): Filter to restrict results to specific location types

Example input: `{"input":"nc"}`

### `vibemcp_create_or_update_campaign`

Create or Update Campaign · Destructive

Create or update a campaign and its strategies. This tool does not publish draft campaigns. Use list_* and get_* tools to search for entity IDs or details when needed. Refuse to modify a campaign that has been archived, this can only be done manually via the dashboard. On validation failures, fix the offending fields and retry. Returns an error if one of the entities referenced in the input does not exist or the caller lacks access. Do not retry if the approval is rejected. For optimization recommendations, `get_business_rules` covers them with domain `campaign_optimization_playbook`.

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

Inputs:

- `campaign` (`object`, required): # Campaign Input Instructions

## Prerequisites
- DRAFT campaigns are fully editable. PUBLISHED campaigns can be edited with restrictions (see "Updating a published campaign"). ARCHIVED/DELETED campaigns are read-only.
- A campaign must have at least one strategy

## Creating a campaign
- Include all fields where the description mentions "Required on create".

## Updating a campaign
- The campaign and strategies may have changed since your last calls, therefore only include fields that need to change. Omit every other field, or set to null, to leave them unchanged.

### Updating a published campaign
The following restrictions apply both the dashboard and this tool:
- Allowed: rename, optimization goal, attribution window, pause/resume (the `active` field on the campaign or a strategy), strategy budgets/bids/targeting/creatives/end dates, and adding new strategies.
- Not allowed: changing the campaign advertiser/goal, changing an existing strategy budget type or start date, deleting strategies.

Example input: `{"campaign":{}}`

### `vibemcp_prepare_creative_upload`

Prepare Creative Upload · Destructive

Prepare a direct MP4 upload for an advertiser. Post a multipart form directly to uploadUrl using every returned field and a file part, then call upload_creative with source.type="upload" and the returned uploadId. The video must be 100 KiB to 500 MiB and use Content-Type video/mp4. If campaignId is supplied, omit strategyIds only when the campaign has exactly one active strategy.

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

Inputs:

- `advertiserId` (`string`, required): Advertiser UUID that will own the creative.
- `campaignId` (`string`, optional): Campaign UUID to attach the creative to after creation.
- `isAiGeneratedVideo` (`boolean`, optional): Whether an AI system generated the video. Default: `false`.
- `strategyIds` (`string`, optional): Strategy UUIDs within campaignId. Omit only when the campaign has exactly one strategy.

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

### `vibemcp_publish_campaign`

Publish Campaign · Destructive

Publish a draft campaign. Only call this after explicit user confirmation, because publishing is a non-reversible user-facing action that starts ad delivery and spend. On validation failures, do not retry but instead explain the errors in a user-friendly way and suggest modifications. Returns an error if the campaign is not in draft, if it does not exist, or if the caller lacks access.

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

Inputs:

- `campaignId` (`string`, required): The ID of the DRAFT campaign to publish

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

### `vibemcp_upload_creative`

Upload Creative · Destructive

Upload an MP4 into an advertiser creative library. For source.type="upload": finalize a direct upload prepared with prepare_creative_upload after posting the multipart form. Repeat with this source type while status is processing.For source.type="url": provide a public HTTPS MP4. The first call queues asynchronous ingestion and immediately returns status="processing" with uploadId; poll only with source.type="upload" and that uploadId afterward. Polling returns status="failed" with a safe error if ingestion fails. Each URL submission creates a new upload. For both source types, this returns a stable creativeId after existing CTV validation succeeds and optionally attaches it to campaign strategies.

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

Inputs:

- `advertiserId` (`string`, required): Advertiser UUID that will own the creative.
- `name` (`string`, required): Creative name shown in the advertiser library.
- `source` (`object`, required): No description.
- `campaignId` (`string`, optional): Campaign UUID to attach the creative to after creation.
- `isAiGeneratedVideo` (`boolean`, optional): Whether an AI system generated the video. Default: `false`.
- `strategyIds` (`string`, optional): Strategy UUIDs within campaignId. Omit only when the campaign has exactly one strategy.

Example input: `{"advertiserId":"<advertiserId>","name":"<name>","source":{}}`

## Related

Other Marketing connectors ([all 190](/agentkit/connectors/?category=marketing)):

- [HubSpot](/agentkit/connectors/hubspot/): Scalekit connector, OAuth, 457 tools
- [Mailchimp](/agentkit/connectors/mailchimp/): Scalekit connector, OAuth, 73 tools
- [Twitter / X](/agentkit/connectors/twitteroauth/): Scalekit connector, OAuth, 92 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 |
