Microfn MCP Server

The Model Context Protocol (MCP) enables AI assistants to securely connect to your external systems and data. With MicroFn's MCP integration, your AI assistants can directly trigger and interact with your serverless functions.

This integration provides another powerful way to trigger MicroFn functions beyond HTTP requests, allowing for dynamic, AI-driven interactions with your serverless infrastructure.

For AI assistants like Claude that support remote MCP servers:

1. Open your AI assistant's remote MCP / integrations page
2. Add the MicroFn MCP server URL:

https://mcp.microfn.dev/sse

The setup process will guide you through authentication with your MicroFn account.

For local MCP clients, configure your MCP client with the following settings:

{
  "mcpServers": {
    "microfn": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.microfn.dev/sse"]
    }
  }
}

This configuration will prompt you to authenticate with MicroFn when first connecting.

MicroFn uses Personal Access Tokens (PATs) for MCP authentication. When you first connect through MCP, you'll be prompted to:

1. Visit the MicroFn authentication page
2. Generate a new Personal Access Token
3. Provide the token to complete the MCP connection

These tokens can be managed through your account settings and provide secure, scoped access to your MicroFn functions.

Once connected, AI assistants can:

• Discover and list your available functions
• Execute functions with parameters
• Retrieve function execution results
• Access function metadata and documentation
• Monitor function performance and logs

This enables powerful AI-driven workflows and automation using your serverless functions.

Learn more about MCP and how to use it effectively:

• MicroFn MCP Server Source Code
• Model Context Protocol Documentation