MCP Docs Server
Provides direct access to local documentation files through simple search and overview tools, enabling LLMs to query project-specific markdown documentation without requiring vector databases or RAG pipelines.
README
MCP Docs Server
A lightweight Model Context Protocol (MCP) server that provides direct access to local documentation files - a simple alternative to complex RAG pipelines for project-specific context.
Overview
This MCP server reads a single markdown file (context.md) and exposes its contents through two simple tools:
get_context_overview(): Lists all section titlessearch_context(query): Searches content across all sections
Perfect for giving LLMs access to project documentation without the overhead of vector databases or embedding models.
Features
- Zero dependencies beyond the MCP Python SDK
- Lightning fast - direct file access, no vector search
- Simple setup - works with both GUI and CLI MCP clients
- Cross-platform - includes shell wrapper for macOS/Linux compatibility
- Robust error handling - comprehensive logging and debugging support
Installation
Prerequisites
- Python 3.11+
- MCP client (Claude Desktop, cline, etc.)
Setup
- Clone this repository:
git clone https://github.com/unlock-mcp/mcp-docs-server.git
cd mcp-docs-server
- Install dependencies:
pip install -r requirements.txt
- Create your documentation file:
# Create a context.md file in the project root with your documentation
echo "# My Project Docs\n\nThis is my documentation." > context.md
Client Configuration
For Claude Desktop (GUI clients)
Use the shell wrapper for reliable execution:
- Make the wrapper executable:
chmod +x run_context_server.sh
- Install the server:
mcp install ./run_context_server.sh --name "docs-server"
For cline and CLI clients
Add to your MCP configuration file:
{
"mcpServers": {
"docs-server": {
"timeout": 60,
"type": "stdio",
"command": "/opt/homebrew/bin/python3.11",
"args": [
"/path/to/mcp-docs-server/mcp_context_server.py"
],
"env": {}
}
}
}
Note: Update the Python path to match your system (which python3.11)
Development
Testing
Use the MCP development tools for easy testing:
mcp dev ./run_context_server.sh
This launches a web-based inspector for testing your server.
Debugging
The server logs to stderr for debugging. Check your MCP client's logs if you encounter issues.
Common issues:
- ENOENT errors: Use the shell wrapper or specify full Python path
- Import errors: Ensure
mcp[cli]>=1.2.0is installed - File not found: Verify
context.mdexists in the project root
File Structure
mcp-docs-server/
├── mcp_context_server.py # Main server implementation
├── run_context_server.sh # Shell wrapper for GUI clients
├── requirements.txt # Python dependencies
├── context.md # Your documentation (create this)
└── README.md # This file
Usage
Once configured, you can use these tools in your MCP client:
- Get overview: "What sections are available in the docs?"
- Search content: "Search for authentication in the docs"
- Specific queries: "How do I configure the database?"
Tutorial
For a complete walkthrough of building this server from scratch, including common pitfalls and solutions, see the full tutorial: Ditching RAG: Building a Local MCP Server for Your Docs
Contributing
Contributions welcome! Please feel free to submit issues and pull requests.
License
MIT License - see LICENSE file for details.
Built with ❤️ by the UnlockMCP team.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.