Zapier MCP for Python: setup with a connection token

Connect your Python code to Zapier MCP by creating a server and generating a connection token, then connecting with an MCP client SDK over Streamable HTTP.

This page shows how to connect your Python code to Zapier MCP using a connection token.

Before you begin

• A Zapier account.
• Python 3.10 or later.

Connect Python to Zapier MCP

1. Create an MCP server

   • Go to mcp.zapier.com.
   • Click Add MCP server.
   • Under Choose your AI agent, search for and select Python.
2. Generate a connection token

   • Select the Settings tab.
   • In the API token section, click Generate token.
   • Copy the Token.

   The token is only shown once. If you lose it, click Rotate token to get a new one. The previous token stops working straight away, so update anywhere you used it.

   Treat your connection token like a password. Anyone with it can run tools on this server and access your data.

3. Set your token as an environment variable

   export ZAPIER_MCP_TOKEN="YOUR_ZAPIER_MCP_TOKEN"
   
4. Install FastMCP

   pip install fastmcp
   

   Or with uv:

   uv pip install fastmcp
   
5. Connect and list your tools

   This script uses FastMCP, but any MCP SDK that supports Streamable HTTP works. It sends your token in an Authorization: Bearer header:

   import asyncio
   import json
   import os
   
   from fastmcp import Client
   from fastmcp.client.transports import StreamableHttpTransport
   
   # Create the transport with your MCP server URL and token
   # The token is read from the ZAPIER_MCP_TOKEN environment variable
   server_url = "https://mcp.zapier.com/api/v1/connect"
   api_key = os.environ["ZAPIER_MCP_TOKEN"]
   transport = StreamableHttpTransport(
       server_url,
       headers={"Authorization": f"Bearer {api_key}"}
   )
   
   # Initialize the client with the transport
   client = Client(transport=transport)
   
   
   async def main():
       # Connection is established here
       print("Connecting to MCP server...")
       async with client:
           print(f"Client connected: {client.is_connected()}")
   
           # Make MCP calls within the context
           print("Fetching available tools...")
           tools = await client.list_tools()
   
           print(f"Available tools: {json.dumps([t.name for t in tools], indent=2)}")
   
       # Connection is closed automatically when exiting the context manager
       print("Example completed")
   
   
   if __name__ == "__main__":
       asyncio.run(main())
   

You’ve now connected Python to Zapier MCP.

Next steps

How tools work

What each meta-tool does, and how dynamic tool discovery works.

How connections work

How connection tokens work, and how to manage them.