Anthropic API

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.

   PythonCopy

   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"],
   )

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

Keys are created under 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.

All clients