MCP.so
Sign In

MCP SERVER

@JeanVittory

Repository

About MCP SERVER

With this MCP, you can debug your application by querying any issue to an LLM using the latest documentation available on the web. We currently support LangChain, LlamaIndex, and OpenAI docs, but you can add any other sources as needed.

#mcp-server#debugging#documentation-query

Basic information

Category

AI & Agents

Runtime

python

Transports

stdio

Publisher

JeanVittory

Config

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

{
  "mcpServers": {
    "mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "/ABSOLUTE/PATH/TO/YOUR/mcp-server-code",
        "run",
        "src/main.py"
      ],
      "env": {
        "SERPER_API_KEY": ""
      }
    }
  }
}

Tools

No tools detected

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?

MCP SERVER is a Model Context Protocol server that enables queries about any issue using the latest documentation available on the web. It currently supports LangChain, LlamaIndex, and OpenAI documentation, and is designed for developers debugging their applications.

How to use MCP SERVER?

Clone the repository, create a Python 3.12 virtual environment, activate it, and install with uv pip install -e .. Obtain a Serper API key and set it as an environment variable. Configure the MCP client (e.g., Claude Desktop) with the provided JSON snippet pointing to src/main.py. The server is invoked via the MCP client.

Key features of MCP SERVER

  • Query issues using the latest web documentation.
  • Supports LangChain, LlamaIndex, and OpenAI docs.
  • Easily add more documentation sources by editing a constant.
  • Uses Serper API for web search.
  • Built with Python 3.12.9, BeautifulSoup4, and MCP CLI.

Use cases of MCP SERVER

  • Debugging an application by searching for recent solutions.
  • Retrieving the most current answers from official documentation.
  • Extending the knowledge base by adding custom documentation URLs.

FAQ from MCP SERVER

How do I install MCP SERVER?

Clone the GitHub repository, create a Python 3.12 virtual environment, activate it, and run uv pip install -e . inside the project directory.

What environment variable is required?

You need a Serper API key. Set it as the environment variable SERPER_API_KEY (generated at serper.dev).

How can I add more documentation sources?

Open the docs_urls variable in the constants folder and add the URLs of the documentation you want to reference to that dictionary.

What if I encounter an issue?

Contact the author at [email protected] or submit an issue on the GitHub repository.

Comments

More AI & Agents MCP servers

🔎 GPT Researcher

assafelovic

An autonomous agent that conducts deep research on any data using any LLM providers

28.1K

1MCP - One MCP Server for All

1mcp-app

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

468

MCP Claude Code

SDGLBL

MCP implementation of Claude Code capabilities and more

302

Sequential Thinking Multi-Agent System (MAS)

FradSer

An advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.

306

MCP Client for Ollama (ollmcp)

jonigl

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre

768