servers VS python-sdk

Most agents don't speak raw HTTP — they speak MCP. So the real distribution surface is a tiny MCP server that exposes each endpoint as a tool and does the paying under the hood. The agent calls web_search(query); the server hits the paid endpoint, handles the 402 with its operator's wallet, returns JSON. One line to install:

The Model Context Protocol (MCP) is an open standard for connecting AI hosts (Claude, ChatGPT, Cursor, VS Code, and others) to external context and actions through a structured protocol instead of ad-hoc plugins.

Model Context Protocol specification

That changed when I built mpesa-mcp — a Model Context Protocol server that wraps the Daraja API and makes it directly available to Claude, GPT-4, and Gemini.

If you haven't run into it yet, MCP (Model Context Protocol) is an open standard for exposing tools to AI agents. two-go ships an MCP server that runs over stdio with no dependencies, no URL, no account, and no API key. It's all local.

MCP server surface. The CLI is already agent-friendly, so I'm double minded about whether a Model Context Protocol server would make integration smoother. I'm personally not a fan of MCP and prefer skills and CLIs.

As noted in the Model Context Protocol (MCP) Introduction, this protocol allows Claude to interact with systems like GitHub and local databases through a standardized interface.

Keep the project's living context: current task state, decisions, conventions, known footguns as plain Markdown committed to the repo, and expose it to the agent over MCP.

The MCP ecosystem doubles every few months. Bookmark the official MCP servers repository for the canonical list.

Today's example was modelcontextprotocol/python-sdk#2657. I opened it eleven days ago. A small fix on the v1.x backport branch: when a client POSTs a JSON-RPC request whose id matches one already in flight on the same session, reject the duplicate with 409 Conflict instead of silently overwriting the prior _request_streams entry. The MCP base protocol explicitly forbids reusing a request ID within a session; the silent-overwrite behavior left the first request hanging forever.

If you'd rather hand-roll it, the Python SDK and TypeScript SDK are both solid and the protocol itself is small enough to read in an afternoon.

数据来源：MCP Python SDK — FastMCP — 23,020 ⭐

GitHub - modelcontextprotocol/python-sdk: The official Python SDK for Model Context Protocol servers and clients

These are the tests that catch the kinds of misleading errors, state leakage, and contract drift seen in modelcontextprotocol/typescript-sdk #699, modelcontextprotocol/python-sdk #756, and modelcontextprotocol/typescript-sdk #451 before users do. A server with only happy-path coverage is usually one incident away from rediscovering Sloth, Wrath, or Pride the hard way.

The MCP fault taxonomy paper cites a Graphiti MCP issue in which returning full embedding vectors increased output from approximately 5K tokens to more than 250K tokens, reportedly driving a 50x increase in cost. The pattern also appears in runtime excess issues like modelcontextprotocol/python-sdk #756, where stateless Streamable HTTP leaked tasks across requests, a form of runtime gluttony even when the payload itself was not large.

https://github.com/modelcontextprotocol/python-sdk/commits?a...

Many contributors to the python sdk continued to iterate on the mcp server implementation using the name fastmcp ( since it had been donated to the project ) resulting in growing interest:

The official Python SDK documentation is at modelcontextprotocol.io/docs/develop/build-server. The source code is at github.com/modelcontextprotocol/python-sdk.

Python with FastMCP (the official MCP Python SDK)