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

LinkedIn MCP Server

stickerdaniel

Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, and messages.

2.7K

MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages

utensils

MCP-NixOS - Model Context Protocol Server for NixOS resources

739

Solon Ai

opensolon

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

416

Mcp Agent

lastmile-ai

Build effective agents using Model Context Protocol and simple workflow patterns

8.4K

21st.dev Magic AI Agent

21st-dev

It's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic

5.3K