MCP Docs Search Server
by RohitKrish46
A lightweight MCP server that searches and retrieves relevant documentation content from popular AI libraries like LangChain, LlamaIndex, and OpenAI using a combination of web search and content parsing. This project allows Language Models to query and fetch up-to-date documentation content dynamically, acting as a bridge between LLMs and external doc sources.
Last updated: N/A
What is MCP Docs Search Server?
The MCP Docs Search Server is a lightweight server that implements the Model Context Protocol (MCP) to provide Language Models with access to up-to-date documentation from popular AI libraries. It acts as a bridge between LLMs and external documentation sources, allowing them to dynamically query and retrieve relevant information.
How to use MCP Docs Search Server?
To use the server, you need to clone the repository, set up a virtual environment, install dependencies, and configure your Serper API key. Then, you can integrate the server as a tool within Claude Desktop by updating the claude_desktop_config.json file. The core tool is get_docs(query: str, library: str) which accepts a search query and a library name (langchain, llama-index, or openai).
Key features of MCP Docs Search Server
Web Search Integration using Serper API
Clean Content Extraction using BeautifulSoup
Seamless LLM Tooling with get_docs tool
Support for LangChain, LlamaIndex, and OpenAI documentation
Use cases of MCP Docs Search Server
Providing LLMs with up-to-date information from documentation
Enabling LLMs to answer questions based on the latest documentation
Building LLM agents that can query specific libraries in real time
Creating a scalable ecosystem of services for LLMs
FAQ from MCP Docs Search Server
What is MCP?
What is MCP?
Model Context Protocol is an open standard that enables developers to build secure, two-way connections between their data sources and AI-powered tools.
What libraries are supported?
What libraries are supported?
Currently, the server supports LangChain, LlamaIndex, and OpenAI.
How do I add more libraries?
How do I add more libraries?
You can add more libraries by updating the docs_urls dictionary.
How does the server extract clean content?
How does the server extract clean content?
The server uses BeautifulSoup to parse HTML content and extract clean, human-readable text, stripping away unnecessary tags, ads, or navigation content.
How do I integrate this server with Claude Desktop?
How do I integrate this server with Claude Desktop?
Open Claude Desktop → File > Settings > Developer > Edit Config. Update your claude_desktop_config.json to include the mcpServers configuration.