Pymcp MCP Server

A lightweight, flexible implementation of the Model Context Protocol (MCP) for Python applications, specializing in robust HTTP/SSE transport. Exposed over MCP by the pymcp mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

• Modular Framework — Clean implementation of BaseMCPServer, BaseMCPClient, and MultiMCPClient
• HTTP/SSE Transport — Robust HTTP/SSE implementation with automatic session management, configurable timeouts, and reconnection handling
• Concurrent Task Execution — BaseMCPServer.run_with_tasks() method for easily running servers with persistent background asynchronous tasks
• Tool Registration & Discovery — Simple decorator-based tool registration (@server.register_tool()) and a standard describe_tools endpoint for clients to dynamically query detailed tool capabilities (parameters, descriptions)
• Server Push — Built-in support for server-initiated push notifications to clients and periodic keep-alive pings. Includes NotificationScheduler helper class
• LLM Integration — Includes BaseLLMClient abstraction for easy integration with various LLM providers (an Anthropic Claude example is provided)

Adding it to your client

The server ships on PyPI as pymcp-sse, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Configuration

You will need one environment variable: ANTHROPIC_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Caveats

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the pymcp mcp server does with a few real requests.

When to reach for it

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.