MCP Python

Provides an MCP server in Python to search arXiv papers and extract paper information, with room to extend with more MCP tools.

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months 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": {
    "vnkishortech-mcp_python": {
      "command": "python",
      "args": [
        "mcp_server/server.py"
      ]
    }
  }
}

You can run a Python MCP server that provides a minimal, extensible framework for Model Context Protocol (MCP) interactions. It can search for arXiv papers and extract details, making it easy to extend with additional MCP tools while keeping a lightweight local server for experimentation and development.

How to use

To use the MCP server, you start the Python process locally and then connect your MCP client to it. The server exposes a standard MCP interface you can extend with new tools. You can search for papers on arXiv, store results, and request specific paper details through the MCP client workflow.

How to install

Prerequisites: You need Python 3.8+ and a virtual environment tool. You will also need an internet connection to install dependencies.

# 1) Clone the project
# (Replace with your actual repository URL after cloning)
git clone <your-repo-url>
cd MCP_Python

# 2) Create and activate a virtual environment
python3 -m venv venv
source venv/bin/activate

# 3) Install dependencies
pip install arxiv

Once dependencies are installed, start the MCP server. This runs the server module that implements the MCP interface.

python mcp_server/server.py

Additional sections

Project structure and notes: the server implementation lives under mcp_server/server.py. It is designed as a lightweight, ready-to-extend MCP server that currently supports searching arXiv and extracting paper information. The project also includes a CI workflow for linting and tests, and a small example directory structure.

Troubleshooting tips: ensure your virtual environment is activated, and that you have network access to install dependencies and access arXiv. If the server fails to start, check for missing dependencies or syntax errors in the server module. You can add additional MCP tools by extending the server with new endpoints that adhere to the MCP interface.

Available tools

search_papers

Search for papers on arXiv and return metadata for matching results.

extract_paper_info

Extract and structure information about a specific paper, such as title, authors, abstract, and metadata.