Skip to content

Create a documented indexing of your codebase/docs to use it with local mcp-server for better providing context to AI

License

Notifications You must be signed in to change notification settings

MaheshDoiphode/mcpdata

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Local MCP System

A comprehensive system for local documentation indexing and AI-powered search through MCP (Model Context Protocol). Enable AI assistants to search across all your documentation and code repositories from a single interface.

🚀 Quick Start

1. Install and Index

cd mcpdata
pip install -e .
mcpdata /path/to/your/docs --workspace-name "My Docs"

2. Start MCP Server

cd mcp-global-server
pip install -r requirements.txt
python server.py

3. Configure AI Client

{
  "mcpServers": {
    "global-docs": {
      "command": "python",
      "args": ["C:\\path\\to\\localmcp\\mcp-global-server\\server.py"]
    }
  }
}

🛠️ GitHub Copilot Configuration

To use with GitHub Copilot, add the MCP server configuration to your VS Code settings:

Location

Create or edit: C:\Users\%UserProfile%\AppData\Roaming\Code\User\mcp.json

Configuration

{
    "servers": {
        "global-docs": {
            "id": "global-docs",
            "name": "global-docs",
            "version": "1.0.0",
            "config": {
                "type": "stdio",
                "command": "C:\\Users\\%UserProfile%\\AppData\\Local\\Programs\\Python\\Python312\\python.exe",
                "args": [
                    "C:\\path\\to\\your\\localmcp\\mcp-global-server\\server.py"
                ],
                "env": {
                    "MCP_REGISTRY_PATH": "C:\\Users\\%UserProfile%\\Documents\\mcpdata"
                }
            }
        }
    },
    "inputs": []
}

Note: Replace the paths with your actual Python installation and project location.

🎮 Examples

Search Across Documentation and Code

You: "Search for mcp configuration"

Search Results

Get Complete File Contents

You: "Get the contents of the initializer file"

Get Contents

🏗️ Architecture

localmcp consists of two components:

  1. mcpdata - Fast indexing engine
  2. mcp-global-server - MCP server for AI

Flow: Index files → Create searchable database → AI searches via MCP

📊 What You Can Search

  • Documentation: .md, .rst, .txt, .adoc
  • Code: .py, .js, .ts, .java, .cpp, .rs
  • Config: .json, .yaml, .yml, .toml

🔗 Documentation

🎯 Use Cases

  • Documentation Teams - Search across multiple doc repositories
  • Development Teams - Find code patterns across repositories
  • Mixed Projects - Unified search for docs + code

📜 License

MIT License - see LICENSE file for details.


Ready to get started? Follow the Quick Start above or read the Complete Installation Guide.

About

Create a documented indexing of your codebase/docs to use it with local mcp-server for better providing context to AI

Topics

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages