About mc-server-demo
mc-server-demo is an MCP server for retrieving the latest documentation for a queried library. It is aimed at clients that need current library references and uses Serper API search.
Key features
- 01Retrieve current library documentation
- 02Search through Serper API
- 03Expose the get_docs tool
Use cases
- 01Look up documentation while coding
- 02Fetch current references for a library
MCP support
The MCP server exposes a `get_docs` tool that accepts queries and retrieves library documentation. It uses Serper API for search.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmc-server-demo
A Model Context Protocol (MCP) server implementation that can retieve the latest documentation of a queried library.
Setup locally
- The MCP tool is using Serper API to seach or Google therefore an api key should be specified. See .env.example on how to define it.
- Create a virtual environment:
python -m venv .venv - Activate the virtual environemt:
source .venv/bin/activate - Install the required dependencies:
pip install -r requirements.txt
Debug
- Run usin Model Context Protocol inspector:
npx @modelcontextprotocol/inspector python main.py - Visit the local inspector url displayed on terminal.
- List the available tools and use
get_docsto input queries.
Client integration
- Example of Cursor IDE
- Navigate to AI settings
- Under "Custom MCP Server", add the following configuration:
{ "command": "${workspaceFolder}/.venv/bin/python", "args": ["main.py"] }
License
This project is licensed under the MIT License - see the LICENSE file for details.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.