{
  "markdown": "# Paper Search MCP\n\nA Model Context Protocol (MCP) server for searching and downloading academic papers from multiple sources, including arXiv, PubMed, bioRxiv, and Sci-Hub (optional). Designed for seamless integration with large language models like Claude Desktop.\n\n![PyPI](https://img.shields.io/pypi/v/paper-search-mcp.svg) ![License](https://img.shields.io/badge/license-MIT-blue.svg) ![Python](https://img.shields.io/badge/python-3.10+-blue.svg)\n[![smithery badge](https://smithery.ai/badge/@openags/paper-search-mcp)](https://smithery.ai/server/@openags/paper-search-mcp)\n\n---\n\n## Table of Contents\n\n- [Overview](#overview)\n- [Features](#features)\n- [Installation](#installation)\n  - [Quick Start](#quick-start)\n    - [Install Package](#install-package)\n    - [Configure Claude Desktop](#configure-claude-desktop)\n  - [For Development](#for-development)\n    - [Setup Environment](#setup-environment)\n    - [Install Dependencies](#install-dependencies)\n- [Contributing](#contributing)\n- [Demo](#demo)\n- [License](#license)\n- [TODO](#todo)\n\n---\n\n## Overview\n\n`paper-search-mcp` is a Python-based MCP server that enables users to search and download academic papers from various platforms. It provides tools for searching papers (e.g., `search_arxiv`) and downloading PDFs (e.g., `download_arxiv`), making it ideal for researchers and AI-driven workflows. Built with the MCP Python SDK, it integrates seamlessly with LLM clients like Claude Desktop.\n\n---\n\n## Features\n\n- **Multi-Source Support**: Search and download papers from arXiv, PubMed, bioRxiv, medRxiv, Google Scholar, IACR ePrint Archive, Semantic Scholar.\n- **Deep Research Ready**: Provides the standardized `search` and `fetch` tools required by OpenAI Deep Research and ChatGPT connectors.\n- **Standardized Output**: Papers are returned in a consistent dictionary format via the `Paper` class.\n- **Asynchronous Tools**: Efficiently handles network requests using `httpx`.\n- **MCP Integration**: Compatible with MCP clients for LLM context enhancement.\n- **Extensible Design**: Easily add new academic platforms by extending the `academic_platforms` module.\n\n---\n\n## Installation\n\n`paper-search-mcp` can be installed using `uv` or `pip`. Below are two approaches: a quick start for immediate use and a detailed setup for development.\n\n### Installing via Smithery\n\nTo install paper-search-mcp for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@openags/paper-search-mcp):\n\n```bash\nnpx -y @smithery/cli install @openags/paper-search-mcp --client claude\n```\n\n### Quick Start\n\nFor users who want to quickly run the server:\n\n1. **Install Package**:\n\n   ```bash\n   uv add paper-search-mcp\n   ```\n\n2. **Configure Claude Desktop**:\n   Add this configuration to `~/Library/Application Support/Claude/claude_desktop_config.json` (Mac) or `%APPDATA%\\Claude\\claude_desktop_config.json` (Windows):\n   ```json\n   {\n     \"mcpServers\": {\n       \"paper_search_server\": {\n         \"command\": \"uv\",\n         \"args\": [\n           \"run\",\n           \"--directory\",\n           \"/path/to/your/paper-search-mcp\",\n           \"-m\",\n           \"paper_search_mcp.server\"\n         ],\n         \"env\": {\n           \"SEMANTIC_SCHOLAR_API_KEY\": \"\" // Optional: For enhanced Semantic Scholar features\n         }\n       }\n     }\n   }\n   ```\n   > Note: Replace `/path/to/your/paper-search-mcp` with your actual installation path.\n\n### For Development\n\nFor developers who want to modify the code or contribute:\n\n1. **Setup Environment**:\n\n   ```bash\n   # Install uv if not installed\n   curl -LsSf https://astral.sh/uv/install.sh | sh\n\n   # Clone repository\n   git clone https://github.com/openags/paper-search-mcp.git\n   cd paper-search-mcp\n\n   # Create and activate virtual environment\n   uv venv\n   source .venv/bin/activate  # On Windows: .venv\\Scripts\\activate\n   ```\n\n2. **Install Dependencies**:\n\n   ```bash\n   # Install project in editable mode\n   uv add -e .\n\n   # Add development dependencies (optional)\n   uv add pytest flake8\n   ```\n\n---\n\n## Contributing\n\nWe welcome contributions! Here's how to get started:\n\n1. **Fork the Repository**:\n   Click \"Fork\" on GitHub.\n\n2. **Clone and Set Up**:\n\n   ```bash\n   git clone https://github.com/yourusername/paper-search-mcp.git\n   cd paper-search-mcp\n   pip install -e \".[dev]\"  # Install dev dependencies (if added to pyproject.toml)\n   ```\n\n3. **Make Changes**:\n\n   - Add new platforms in `academic_platforms/`.\n   - Update tests in `tests/`.\n\n4. **Submit a Pull Request**:\n   Push changes and create a PR on GitHub.\n\n---\n\n## Demo\n\n<img src=\"docs\\images\\demo.png\" alt=\"Demo\" width=\"800\">\n\n## TODO\n\n### Planned Academic Platforms\n\n- [√] arXiv\n- [√] PubMed\n- [√] bioRxiv\n- [√] medRxiv\n- [√] Google Scholar\n- [√] IACR ePrint Archive\n- [√] Semantic Scholar\n- [ ] PubMed Central (PMC)\n- [ ] Science Direct\n- [ ] Springer Link\n- [ ] IEEE Xplore\n- [ ] ACM Digital Library\n- [ ] Web of Science\n- [ ] Scopus\n- [ ] JSTOR\n- [ ] ResearchGate\n- [ ] CORE\n- [ ] Microsoft Academic\n\n---\n\n## License\n\nThis project is licensed under the MIT License. See the LICENSE file for details.\n\n---\n\nHappy researching with `paper-search-mcp`! If you encounter issues, open a GitHub issue.\n",
  "bytes": 5168,
  "sha": "4942c5e28b9685f3fa6a8d45057101a4d2da16da584ff254dc89f7e4eb1ad572",
  "repo_slug": "adamamer20/paper-search-mcp-openai",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_ai_smithery_adamamer20_paper_search_mcp__8596e1cb/readme"
}