Fetches and caches documentation for GitHub repositories via Google CodeWiki, enabling search of repository documentation, viewing cached repositories, and managing the documentation cache.
File: README.md
Brief: Comprehensive documentation for the CodeWiki MCP Server project
Copyright (c) 2025 Chris Bunting - https://github.com/cbuntingde
This source code is licensed under the MIT license found in the
LICENSE file in the root directory of this source tree.
CodeWiki MCP Server
An MCP (Model Context Protocol) server that integrates with Google CodeWiki to fetch and cache documentation for GitHub repositories.
Features
Repository Search: Search for GitHub repositories on Google CodeWiki
Documentation Fetching: Retrieve and parse documentation from CodeWiki
Smart Caching: Cache documentation with TTL (Time To Live) to avoid repeated requests
Documentation Search: Search within cached documentation for specific content
Cache Management: List, clear, and manage cached repositories
Installation
Clone this repository
Install dependencies:
npm installBuild the project:
npm run build
Setup
VS Code Integration
The project includes VS Code MCP configuration. The .vscode/mcp.json file is automatically created during setup and configures the server for use with MCP-compatible clients.
Git Configuration
A comprehensive .gitignore file is included to exclude:
Build outputs (
dist/,build/)Cache directories (
.codewiki-cache/)Environment files (
.env*)IDE files (
.vscode/,.idea/)OS files (
.DS_Store,Thumbs.db)Logs and temporary files
Usage
As an MCP Server
This server can be used with any MCP-compatible client. The server provides the following tools:
search_repository
Search for GitHub repositories on Google CodeWiki.
Parameters:
query(string): Search query for repository name or owner/repo format
Example:
get_repository_docs
Get documentation for a specific GitHub repository.
Parameters:
owner(string): Repository owner/organizationrepo(string): Repository nameforce_refresh(boolean, optional): Force refresh cached documentation (default: false)
Example:
search_documentation
Search within cached documentation for a repository.
Parameters:
owner(string): Repository owner/organizationrepo(string): Repository namequery(string): Search query within the documentation
Example:
list_cached_repositories
List all repositories currently cached.
Parameters: None
clear_cache
Clear the documentation cache.
Parameters:
owner(string, optional): Specific repository owner to clearrepo(string, optional): Repository name when clearing specific repo
Examples:
Direct Usage
You can also run the server directly:
Configuration
Cache Settings
The cache manager supports the following configuration:
Default TTL: 24 hours (configurable)
Cache Directory:
.codewiki-cachein the project rootMemory Cache: In-memory cache for frequently accessed data
Disk Cache: Persistent cache stored as JSON files
Environment Variables
CODEWIKI_CACHE_DIR: Custom cache directory pathCODEWIKI_CACHE_TTL: Cache TTL in milliseconds (default: 86400000)
Project Structure
Architecture
Components
Server (
server.ts): Main MCP server implementationCodeWikiClient (
codewiki-client.ts): Client for interacting with Google CodeWikiCacheManager (
cache-manager.ts): Manages caching of documentation
Data Flow
Client requests repository documentation
Server checks cache for existing data
If not cached or expired, fetches from Google CodeWiki
Parses and structures the documentation
Stores in cache for future requests
Returns structured documentation to client
Development
Building
Development Mode
Cleaning
Limitations
No Public API: Google CodeWiki doesn't provide a public API, so this server uses web scraping
Rate Limiting: Be respectful of CodeWiki's servers with appropriate delays
Repository Coverage: Not all repositories may have CodeWiki documentation available
Content Parsing: HTML structure changes on CodeWiki may require updates to the parsing logic
Contributing
Fork the repository
Create a feature branch
Make your changes
Add tests if applicable
Submit a pull request
License
MIT License - see LICENSE file for details.
Author
Chris Bunting cbuntingde@gmail.com