# n8n

The MCP Client Tool node connects an AI Agent node to Zomler.

API key

## Setup

1.  1
    
    Add an MCP Client Tool node to an AI Agent.
    
2.  2
    
    Set the endpoint to the server URL and the transport to HTTP Streamable.
    
    **Endpoint**
    
    ```
    https://api.zomler.com/mcp
    ```
    
3.  3
    
    Under authentication choose Bearer and create a credential holding the key. The agent then lists the platform tools and picks ops itself.
    
4.  4
    
    No agent in the workflow? Call the REST API with an HTTP Request node instead; every op is one POST.
    
    **HTTP Request node**
    
    ```
    POST https://api.zomler.com/api/v1/platforms/instagram
    X-API-Key: zk_live_…
    Content-Type: application/json
    
    { "request": { "op": "profiles", "subjects": ["example"] } }
    ```
    

## What you get

One tool per platform, plus `capabilities` and `check_balance`, at `https://api.zomler.com/mcp`. Every answer is [the envelope](https://zomler.com/docs/api/responses): what was measured, when, what was left out and why, and what it cost. Fresh fetches spend [credits](https://zomler.com/docs/api/credits); anything already held is free.

Keys are created under [API keys](https://app.zomler.com/api-keys) in the dashboard, where each one's calls and spend are listed. Revoking a key stops this client on its next call. The same key also calls the [REST API](https://zomler.com/docs/api).

[All clients](https://zomler.com/docs/mcp)

---

Source: https://zomler.com/docs/mcp/n8n