# Anthropic API

The Messages API's MCP connector calls Zomler on the model's behalf.

API key

## Setup

1.  1
    
    Pass the server in mcp\_servers with the key as its authorization token. The model sees the platform tools and calls them itself.
    
    ```python
    import anthropic, os
    
    client = anthropic.Anthropic()
    response = client.beta.messages.create(
        model="claude-fable-5-1",
        max_tokens=2000,
        messages=[{"role": "user", "content": "How did @example do on Instagram this month?"}],
        mcp_servers=[{
            "type": "url",
            "url": "https://api.zomler.com/mcp",
            "name": "zomler",
            "authorization_token": os.environ["ZOMLER_API_KEY"],
        }],
        betas=["mcp-client-2025-04-04"],
    )
    ```
    

## 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/anthropic-api