servers VS typescript-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.

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.

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.

This pattern shows up in modelcontextprotocol/typescript-sdk #699, where a real tool exception was replaced by a misleading -32602 structured-content error. Once a system starts lying about why it failed, every downstream debugging step gets more expensive. A vague error is not a small quality issue. It is operational debt with interest.

This is the engineering lesson behind modelcontextprotocol/typescript-sdk #451, where subclassing McpServer broke tool argument passing, and modelcontextprotocol/typescript-sdk #745, where generated JSON Schema drifted from what newer clients expected.

Universal CodeMode runs on Cloudflare Workers with R2 for spec storage and KV for caching. The core is TypeScript, using Hono for routing and the MCP TypeScript SDK for the protocol layer.

OpenSeed runs multiple creatures concurrently. The orchestrator spawns Janee once as a child process in HTTP mode. Each creature gets its own MCP session. Janee creates a fresh Server and Transport instance per initialize handshake, following the official MCP SDK pattern.

Model Context Protocol. (n.d.). TypeScript SDK Documentation. Retrieved from https://github.com/modelcontextprotocol/typescript-sdk

Using @ttoss/http-server and @ttoss/http-server-mcp, which are built on top of Koa and the official Model Context Protocol TypeScript SDK, this example showcases how to integrate traditional REST APIs with AI-compatible MCP endpoints in a single application.