arxiv_mcp is an MCP (Metadata and Content Processing) service designed for searching and interpreting academic papers, particularly from arXiv.
- Clone the repository:
git clone https://github.com/your-username/arxiv_mcp.git
- Navigate to the project directory:
cd arxiv_mcp - Install the required dependencies:
pip install -r requirements.txt
To test run the service, use the following command:
mcp dev server.pyEnsure the cline_mcp_settings.json file is properly configured. Example:
{
"mcpServers": {
"arxiv-server": {
"disabled": false,
"timeout": 60,
"command": "/path/to/mcp",
"args": [
"run",
"/path/to/server.py"
],
"env": {
"PATH": "/path/to/env/bin:${env:PATH}"
},
"transportType": "stdio"
}
}
}Contributions are welcome! Please follow these steps:
- Fork the repository.
- Create a new branch:
git checkout -b feature-name
- Commit your changes:
git commit -m "Add feature-name" - Push to your branch:
git push origin feature-name
- Open a pull request.
[Specify the license, e.g., "This project is licensed under the MIT License. See the LICENSE file for details."]