Ultra-lightweight, zero-dependency Python framework to build Model Context Protocol (MCP) servers for Claude.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"py-easy-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# py-easy-mcp ⚡🤖 [](https://pypi.org/project/py-easy-mcp/) [](https://pypi.org/project/py-easy-mcp/) [](https://github.com/lui01212/easy-mcp/blob/main/LICENSE) [](https://github.com/lui01212/easy-mcp/actions) [](https://github.com/lui01212/easy-mcp/issues?q=is%3Aissue+state%3Aopen+label%3A%22good+first+issue%22) [](https://github.com/lui01212/easy-mcp/blob/main/CONTRIBUTING.md) **Ultra-lightweight, zero-dependency Python framework for Model Context Protocol (MCP). Build MCP servers for Claude in seconds.** Turn standard Python functions (both sync and `async def`) into Model Context Protocol tools, resources, and prompt templates for **Claude Desktop** and **Claude Code** with simple decorators. ## Start here: your first contribution **[Featured beginner issue #11](https://github.com/lui01212/easy-mcp/issues/11)**: Write an offline walkthrough of the existing math example. Read [CONTRIBUTING.md](https://github.com/lui01212/easy-mcp/blob/main/CONTRIBUTING.md) for setup, claiming an issue, and opening a draft PR. Repository: `easy-mcp`; PyPI distribution: `py-easy-mcp`; Python import: `easy_mcp`. Both py-easy-mcp and easy-mcp are installed CLI aliases. Try this from a reviewed source checkout, in the repository root, with Python 3.8+. It uses synthetic inputs and needs no API key or network access: ```python from examples.basic_math import mcp print(mcp.call_tool("add", {"a": 2, "b": 3})) ``` Expected output: ```text {'content': [{'type': 'text', 'text': '5'}]…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.