Vikramdse Docs

Provides up-to-date library documentation by querying official sources through Serper API and returning parsed results for MCP clients.

python

GitHub Stars

python

Language

2 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mcp-mirror-vikramdse_docs-mcp-server": {
      "command": "C:\\\\Users\\\\Vikram\\\\.local\\\\bin\\\\uv.exe",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "mcp",
        "run",
        "F:\\\\My Projects\\\\AI\\\\docs-mcp-server\\\\server.py"
      ]
    }
  }
}

This MCP server lets you search and fetch up-to-date documentation for popular libraries using the Serper API. It supports Langchain, Llama-Index, MCP, and OpenAI, helping you access current information even when your language models have knowledge cut-off dates.

How to use

You interact with the server through an MCP client to perform library documentation searches and retrieve relevant pages. Use natural language queries to request documentation about Langchain, Llama-Index, MCP, or OpenAI, and receive parsed, up-to-date results returned by the server. The server runs locally or remotely and uses the Serper API for site-specific searches, then parses the content with BeautifulSoup to present you with targeted information.

How to install

Prerequisites you need before running the MCP server are a Python runtime and access to the MCP runtime tool. You also need a path to the server script that will be executed by the MCP runtime.

Install the MCP runtime and prepare the server script according to your environment. You will run the following command to start the server from your local machine.

C:\Users\Vikram\.local\bin\uv.exe run --with mcp[cli] mcp run F:\My Projects\AI\docs-mcp-server\server.py

Additional notes

Configuration for running this MCP server locally is shown in the command snippet above. The runtime executes the Python server script at the specified path and wires it into the MCP environment so you can issue library documentation queries via your MCP client.

Configuration details

{
  "mcpServers": {
    "docs_mcp_server": {
      "type": "stdio",
      "name": "docs_mcp_server",
      "command": "C:\\Users\\Vikram\\.local\\bin\\uv.exe",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "mcp",
        "run",
        "F:\\My Projects\\AI\\docs-mcp-server\\server.py"
      ]
    }
  }
}

Available tools

search_docs

Performs a natural-language search across library documentation sources and retrieves relevant results to present to the MCP client.

parse_docs

Parses fetched documentation content using a parsing tool to extract structured data and concise summaries for MCP responses.

update_docs

Keeps documentation results current by refreshing content from official sources, ensuring up-to-date information for development and troubleshooting.

Built by

VeilStrat

AI signals for GTM teams