What kind of documentation does McpDocs serve?
It serves documentation about your Elixir project’s functions and the functions of its dependencies.
@josiahdahl
Basic information
Provide documentation about your Elixir project's functions and functions of dependencies to an LLM through an SSE MCP server.
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
McpDocs is an Elixir library that serves documentation about your Elixir project's functions and its dependencies to an LLM (Large Language Model) through an SSE (Server-Sent Events) MCP (Model Context Protocol) server. It is intended for Elixir developers who want to give AI assistants contextual knowledge of their codebase.
Add {:mcp_docs, github: "josiahdahl/mcp_docs", runtime: false, only: [:test, :dev]} to your mix.exs dependencies. Then run mix mcp_docs.start (optionally with --port <port>, default 9702) to start the SSE server. You can also use iex -S mix mcp_docs.start for manual recompiling. Try it out with npx @modelcontextprotocol/inspector.
It serves documentation about your Elixir project’s functions and the functions of its dependencies.
Run `mix mcp_docs.start`; the SSE server listens by default on port 9702. An LLM client can connect to that endpoint.
The package should be added with `runtime: false` and `only: [:test, :dev]`, meaning it is not needed in production.
It uses Server-Sent Events (SSE) as the MCP transport.
No authentication is mentioned, and automatic recompilation is on the roadmap but not yet implemented.

One permissioned folder your team and your AI agents both log into.

Sooveryn gives Claude Code a team of AI personas that remembers your project. Soov, the partner and team lead, keeps your decisions and how you work in a lasting memory, and finds them again by words and by meaning, from
Project context your AI can query through MCP — with source evidence.
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.
Comments