What does GitHub Wiki MCP Server do?
It turns a local GitHub Wiki repository into an MCP server, so applications (like Cursor) can query the wiki and receive relevant page content as context.
@Procrustes5
Basic information
No overview available yet
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.
A server that exposes a locally cloned GitHub Wiki as a Model Context Protocol (MCP) API. It is designed to integrate with editors like Cursor, allowing the editor to retrieve context from the wiki for use in AI-assisted development.
Install by cloning the repository and running npm install, or by globally installing the npm package github-wiki-mcp-server. Configure the wiki path in config/default.js or via the --wiki flag or WIKI_PATH environment variable. Start the server with npm start (or npm run dev for development), then in Cursor add an MCP server pointing to http://localhost:3333/mcp.
It turns a local GitHub Wiki repository into an MCP server, so applications (like Cursor) can query the wiki and receive relevant page content as context.
Node.js 14 or higher and a local clone of a GitHub Wiki repository are required.
Edit `config/default.js` or set the environment variable `WIKI_PATH` to the path of your cloned wiki directory. Alternatively, use the `--wiki` flag when starting the server.
Start the server, then in Cursor’s settings add an external MCP server with the URL `http://localhost:3333/mcp`.
Run `npm install -g github-wiki-mcp-server` and then use the command `github-wiki-mcp` (optionally with `--port` and `--wiki` flags) to start it.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 162 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Model Context Protocol Servers
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.

Ask your Takibi Base collections anything; get answers with cited passages and a support score.

Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths
Comments