Advertise
MCP.so
Sign In

MCP Server for Up-to-Date Library Documentation

@AmirUpSkill

Repository

Basic information

Category

Memory & Knowledge

Transports

stdio

Author

AmirUpSkill

About MCP Server for Up-to-Date Library Documentation

No overview available yet

#mcp-server#documentation#python

MCP Server for Up-to-Date Library Documentation config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "Mcp-Server": {
      "command": "uv",
      "args": [
        "init",
        "mcp-server"
      ]
    }
  }
}

MCP Server for Up-to-Date Library Documentation tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP Server for Up-to-Date Library Documentation?

This project implements an MCP server that provides large language models (LLMs) with real-time access to the latest documentation for specified Python libraries (Langchain, LlamaIndex, OpenAI) before they generate code suggestions. It addresses the problem of LLMs using outdated training data for rapidly evolving libraries.

How to use MCP Server for Up-to-Date Library Documentation?

Install Python 3.11+ and the uv package manager. Obtain a Serper API key from serper.dev and store it in a .env file as SERPER_API_KEY. Run the server with uv run main.py. Then integrate with an MCP client like Claude Desktop (via JSON configuration) or Claude Code (via claude mcp add).

Key features of MCP Server for Up-to-Date Library Documentation

  • Implements the Model Context Protocol for seamless client integration.
  • Exposes a get_docs tool for searching official documentation.
  • Uses Serper API for site‑specific searches (Langchain, LlamaIndex, OpenAI).
  • Fetches and parses documentation content with httpx and BeautifulSoup.
  • Built with Python 3.11+, asyncio, FastMCP, and managed via uv.

Use cases of MCP Server for Up-to-Date Library Documentation

  • A developer asks Claude to write code using Langchain and gets suggestions based on the latest API docs.
  • An LLM‑powered IDE retrieves up‑to‑date LlamaIndex documentation before generating data pipeline code.
  • An AI coding assistant fetches current OpenAI SDK examples to answer a user’s question correctly.

Frequently asked questions

1

Which libraries are supported?

The server searches official documentation for Langchain (`python.langchain.com/docs`), LlamaIndex (`docs.llamaindex.ai/en/stable`), and OpenAI (`platform.openai.com/docs`).

2

What are the runtime requirements?

Python 3.11+, the `uv` package manager, and a Serper API key are required. Node.js/npx is needed only for the optional MCP Inspector debugging tool.

3

How does the server fetch documentation?

It constructs a site‑specific Google search via the Serper API, then uses `httpx` and `BeautifulSoup` to extract text content from the top result pages.

4

How is the server configured?

Create a `.env` file with `SERPER_API_KEY=your_key`. The server runs locally over stdio and connects to MCP clients via configuration (Claude Desktop or Claude Code).

5

Can I test the server without a full client?

Yes. Run the MCP Inspector with `npx @model-context-protocol/inspector "uv run main.py"`, open `http://localhost:5173`, and test the `get_docs` tool with sample queries.

Comments

More Memory & Knowledge MCP servers

Sooveryn

PANDAPROG

Sooveryn gives Claude Code a team of AI personas that remembers your project. Soov, the partner and team lead, keeps your decisions and how you work in a lasting memory, and finds them again by words and by meaning, from

server-noonien - shared memory MCP

sequico

Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.

Azquo

Azquo Holdings Ltd

Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,

Memory

modelcontextprotocol

Model Context Protocol Servers

88.1K

Context7 MCP - Up-to-date Docs For Any Cursor Prompt

upstash

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

58.7K
Advertise