Research Papers MCP Server
Enables LLMs to search and retrieve academic papers from arXiv by topic, author, category, or ID.
README
Research Papers MCP Server
This project is a Model Context Protocol (MCP) server written in Python that acts as an intelligent interface to academic paper repositories, particularly the arXiv API. It allows Large Language Models (LLMs) like Claude to search for and retrieve academic papers.
Features
This server exposes a suite of tools to the LLM, enabling it to:
search_papers: Perform a general topic search for papers from sources like arXiv.find_papers_by_author: Find recent papers by a specific author from sources like arXiv.get_latest_from_category: Browse the newest submissions in a given arXiv category (e.g.,cs.LG).get_paper_by_id: Get full details for a single paper by its arXiv ID.get_papers_by_ids: Efficiently get details for a list of papers by their arXiv IDs.
Requirements
- Python 3.10+
- uv (for environment and package management)
- An MCP Host like Claude for Desktop
Setup and Installation
Installing via Smithery
To install this research papers MCP server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @candenizkocak/research-papers-mcp-server --client claude
Manual Installation
-
Clone the repository:
git clone https://github.com/candenizkocak/research-papers-mcp-server.git research-papers-mcp-server cd research-papers-mcp-server -
Create a virtual environment and install dependencies:
uv venv source .venv/bin/activate # On Windows, use .venv\Scripts\activate uv sync(Note:
uv syncwill install dependencies from thepyproject.tomlfile).
Usage with Claude for Desktop
-
Find the absolute path to your
research-papers-mcp-serverdirectory. -
Open your Claude for Desktop configuration file (
claude_desktop_config.json):- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
- macOS:
-
Add the server configuration, replacing the placeholder with your absolute path:
{ "mcpServers": { "research-papers": { "command": "uv", "args": [ "--directory", "/ABSOLUTE/PATH/TO/research-papers-mcp-server", "run", "arxiv_server.py" ] } } } -
Completely restart Claude for Desktop.
Example Prompts
- General Search: "Find papers about 'mixture of experts models'."
- Author Search: "What are the most recent papers by Geoffrey Hinton?"
- Category Search: "What's new in the cs.LG category on arXiv?"
- Single ID Lookup: "Tell me about arXiv paper 1706.03762."
- Multiple ID Lookup: "Give me details for papers 2307.09288 and 2203.02155."
Acknowledgements
Thank you to arXiv for use of its open access interoperability.
Compliance Notes
Developers and users of this project are responsible for familiarizing themselves with the official arXiv API Terms of Use, API Basics, and API User Manual to ensure full compliance with arXiv's policies, including any rate limits or usage restrictions.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。