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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。