About MicroFn MCP Server (Python)
MicroFn MCP Server (Python) is a remote MCP server for interacting with the microfn platform. It supports remote and local MCP client setups, with authentication prompted during connection.
Key features
- 01Interact with the microfn platform
- 02Connect through Streamable HTTP
- 03Connect through SSE
- 04Authenticate during client setup
Use cases
- 01Access microfn from a remote MCP client
- 02Configure a local client to connect remotely
- 03Develop against a local server
MCP support
It exposes the microfn platform through a remote MCP endpoint. Clients can connect using Streamable HTTP or SSE, or use mcp-remote in a local client.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMicrofn remote MCP
Remote MCP server for interacting with the microfn platform
Setup as remote MCP (eg Claude)
- Open remote MCP / integrations page
- Set
https://mcp.microfn.dev/mcpas URL for the remote MCP
Setup in local MCP clients
- Configure the MCP client
{
"mcpServers": {
"microfn": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.microfn.dev/mcp"]
}
}
}
This will prompt you to authenticate with microfn
- Use
https://mcp.microfn.dev/mcpfor Streamable HTTP - Use
https://mcp.microfn.dev/ssefor SSE (will be phased out)
Local Development
Create a .dev.vars file with local config for auth0 and microfn:
AUTH0_CLIENT_SECRET=xxxx
API_BASE_URL=http://localhost:3000/api
Start a dev server with
wrangler dev
Use the MCP inspector:
npx @modelcontextprotocol/inspector http://localhost:8787/sse
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.