> **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 Metricool MCP server

The Metricool MCP connector routes your AI agent's tool calls to Metricool's own MCP server through Scalekit. Each user signs in to Metricool once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 9 tools.

**Authentication:** OAuth2.1/DCR
**Categories:** Analytics, Marketing, Media
**Tools:** 9: 5 read, 2 write, 2 destructive
**Users sign in with:** OAuth
**OAuth app:** Scalekit's or your own
**Built by:** Vendor MCP
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=METRICOOLMCP)

## What you can do

- **Schedule posts**: schedule posts at a set date and time across one or more social networks
- **Manage scheduled posts**: list and update scheduled posts for a brand
- **Send posts for review**: route new or already scheduled posts through the approval flow
- **Analyze performance**: retrieve analytics for selected metrics over a date range and see which metrics each network offers
- **Find the best time to post**: get recommended posting times for a social network on your account

## 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 Metricool MCP connection

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

   Scalekit credentials are available for Metricool MCP server, so you don't need to register an OAuth app.

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 = 'metricoolmcp'
   const identifier = 'user_123'

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

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

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="metricoolmcp_getanalyticsavailablemetrics",
       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: 'metricoolmcp_getanalyticsavailablemetrics',
  toolInput: {},
  connector: 'metricoolmcp',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="metricoolmcp_getanalyticsavailablemetrics",
    tool_input={},
    connection_name="metricoolmcp",
    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.

### `metricoolmcp_getanalyticsavailablemetrics`

GetAnalyticsAvailableMetrics · Read-only

Get the available analytics metrics for a specific social network and connector in Metricool.

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

Inputs:

- `connector` (`string`, optional): Connector type (e.g. evolution, posts, reels, stories, competitors, hashtags, campaigns, videos)
- `network` (`string`, optional): Social network (e.g. instagram, facebook, twitter, youtube, tiktok, linkedin, pinterest, twitch, bluesky, threads, googleBusinessProfile, metaAds, facebookAds, tiktokAds, brandInfo, website, brandSummary)

Example input: `{}`

### `metricoolmcp_getanalyticsdatabymetrics`

GetAnalyticsDataByMetrics · Read-only

Retrieve analytical data for a Metricool account over a date range based on selected metrics.

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

Inputs:

- `brandId` (`string`, required): Brand id of the Metricool account
- `from` (`string`, required): Start date. Format: ISO 8601 (YYYY-MM-DDTHH:MM:SS±HH:MM)
- `to` (`string`, required): End date. Format: ISO 8601 (YYYY-MM-DDTHH:MM:SS±HH:MM)
- `metrics` (`array`, optional): List of Data Studio field IDs (e.g. IGPO01)

Example input: `{"brandId":"<brandId>","from":"<from>","to":"<to>"}`

### `metricoolmcp_getbesttimetopostbynetwork`

GetBestTimeToPostByNetwork · Read-only

Get the best time to post for a specific social network on a Metricool account.

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

Inputs:

- `brandId` (`string`, required): Blog id of the Metricool brand account to get competitor analytics for
- `fromDate` (`string`, required): Init date of the period to get the data. Format: ISO 8601 (YYYY-MM-DDTHH:MM:SS±HH:MM)
- `socialNetwork` (`string`, required): Provider of the post. The format is "twitter", "facebook", "instagram", "linkedin", "youtube", "tiktok". Only these are accepted.
- `timezone` (`string`, required): Timezone of the post. Format: IANA identifier. Use the timezone from getBrandSettings tool
- `toDate` (`string`, required): End date of the period to get the data. Format: ISO 8601 (YYYY-MM-DDTHH:MM:SS±HH:MM)

Example input: `{"brandId":"<brandId>","fromDate":"<fromDate>","socialNetwork":"<socialNetwork>","timezone":"<timezone>","toDate":"<toDate>"}`

### `metricoolmcp_getbrandsettings`

GetBrandSettings · Read-only

Get the list of brands from your Metricool account. Only Instagram, Facebook, Twitch, YouTube, Twitter, and Bluesky support competitors.

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

Inputs: none.

Example input: `{}`

### `metricoolmcp_getscheduledposts`

GetScheduledPosts · Read-only

Get the list of scheduled posts for a specific Metricool brand.

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

Inputs:

- `brandId` (`string`, required): Blog id of the Metricool brand account
- `fromDate` (`string`, required): Start date. Format: ISO 8601 (YYYY-MM-DDTHH:MM:SS±HH:MM)
- `timezone` (`string`, required): Timezone of the post. Format: IANA identifier
- `toDate` (`string`, required): End date. Format: ISO 8601 (YYYY-MM-DDTHH:MM:SS±HH:MM)
- `extendedRange` (`boolean`, optional): When true, search date range is expanded one day before and after. Default: false. Default: `false`.

Example input: `{"brandId":"<brandId>","fromDate":"<fromDate>","timezone":"<timezone>","toDate":"<toDate>"}`

### `metricoolmcp_createscheduledpost`

CreateScheduledPost · Write

Schedule a post to Metricool at a specific date and time across one or more social networks.

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

Inputs:

- `blogId` (`string`, required): Blog id of the Metricool brand account
- `date` (`string`, required): Publication date/time. Format: ISO 8601 (YYYY-MM-DDTHH:MM:SS±HH:MM)
- `info` (`string`, required): JSON-encoded post data including providers, text, publicationDate, media, networkData, etc.
- `mediaFiles` (`array`, optional): Files from ChatGPT file picker. Each item has download_url (required), file_id (required), mime_type, file_name.

Example input: `{"blogId":"<blogId>","date":"<date>","info":"<info>"}`

### `metricoolmcp_updatescheduledpost`

UpdateScheduledPost · Write

Update a scheduled post in Metricool. Requires the post id and uuid from getScheduledPosts.

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

Inputs:

- `blogId` (`string`, required): Blog id of the Metricool brand account
- `id` (`string`, required): Id of the post to update
- `info` (`string`, required): JSON-encoded post data with full original content plus modifications
- `uuid` (`string`, required): Uuid of the post to update
- `mediaFiles` (`array`, optional): Files from ChatGPT file picker. Each item has download_url (required), file_id (required), mime_type, file_name.

Example input: `{"blogId":"<blogId>","id":"<id>","info":"<info>","uuid":"<uuid>"}`

### `metricoolmcp_createscheduledpostforreview`

CreateScheduledPostForReview · Destructive

Schedule a new post and send it to review (approval flow) in Metricool, replicating the web "Send for review" action.

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

Inputs:

- `approvalSystem` (`string`, required): Approval system: any, all or optional
- `blogId` (`string`, required): Blog id of the Metricool brand account
- `date` (`string`, required): Publication date/time once approved. Format: ISO 8601 (YYYY-MM-DDTHH:MM:SS±HH:MM)
- `info` (`string`, required): Data of the post to be scheduled. Same JSON structure as createScheduledPost.
- `reviewers` (`string`, required): Comma-separated list of reviewer emails
- `notify` (`boolean`, optional): Notify internal Metricool reviewers by email. Default true. External reviewers are always emailed.

Example input: `{"approvalSystem":"<approvalSystem>","blogId":"<blogId>","date":"<date>","info":"<info>","reviewers":"<reviewers>"}`

### `metricoolmcp_sendscheduledpostforreview`

SendScheduledPostForReview · Destructive

Send an already-scheduled post to review (approval flow) in Metricool. Requires the post id and uuid from getScheduledPosts.

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

Inputs:

- `approvalSystem` (`string`, required): Approval system: any, all or optional
- `blogId` (`string`, required): Blog id of the Metricool brand account
- `id` (`string`, required): Id of the already scheduled post
- `info` (`string`, required): Full content of the post to send to review, same JSON structure as updateScheduledPost
- `reviewers` (`string`, required): Comma-separated list of reviewer emails
- `uuid` (`string`, required): Uuid of the already scheduled post
- `notify` (`boolean`, optional): Notify internal Metricool reviewers by email. Default true. External reviewers are always emailed.

Example input: `{"approvalSystem":"<approvalSystem>","blogId":"<blogId>","id":"<id>","info":"<info>","reviewers":"<reviewers>","uuid":"<uuid>"}`

## Related

Other Analytics connectors ([all 127](/agentkit/connectors/?category=analytics)):

- [Microsoft 365](/agentkit/connectors/microsoft365/): Scalekit connector, OAuth, 317 tools
- [HubSpot](/agentkit/connectors/hubspot/): Scalekit connector, OAuth, 457 tools
- [Snowflake](/agentkit/connectors/snowflake/): Scalekit connector, OAuth, 42 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 |
