Skip to main content
Glama
mcp-server-skeleton

mcp-server-skeleton

mcp-server-skeleton

A minimal Model Context Protocol (MCP) server skeleton β€” stdlib only (JSON-RPC 2.0 over stdio). Implements the core handshake (initialize, tools/list, tools/call) so you can register your own tools with zero external dependencies. Wire in Shopify / Meta Ads / Supabase / n8n and expose them to Claude, Cursor, Codex, Gemini, or Hermes.

Original project, aligned with the "Agent Skills / MCP" trend. Not another MCP directory β€” a runnable server you extend.

Register a tool

from mcp_server import MCPServer

server = MCPServer("my-tools", "0.1.0")
server.register_tool(
    "add", "Add two numbers",
    {"type": "object", "properties": {"a": {"type": "number"}, "b": {"type": "number"}}},
    lambda args: str(args["a"] + args["b"]),
)
server.serve_stdio()

Related MCP server: mini-mcp-demo

Testing

pip install -e ".[dev]"
pytest

License

MIT β€” see LICENSE.


Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Exposes a verified tool registry (calculator, sandboxed file read, web fetch) over MCP stdio, enabling any MCP-capable client to reuse the same tools from the inspectable ReAct loop.
      3
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables local tool calling over Model Context Protocol via stdio, providing deterministic tools such as calc.add, text.word_count, and text.summarize_naive after JSON-RPC handshake and discovery.
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables AI clients to call small utility tools like echo and Markdown-to-PDF conversion, running locally over stdio.
      2
      MIT