MCP Paper Finder
MCP server for searching, downloading, and reading academic papers from multiple sources such as arXiv, Google Scholar, and Elsevier.
README
MCP Paper Finder ๐๐
A modular, extensible Model Context Protocol (MCP) server for searching, downloading, and reading academic papers from multiple sources, including arXiv, Zenodo, bioRxiv, medRxiv, CrossRef, Google Scholar, ResearchGate, Sci-Hub, and Elsevier.

Features โจ
- Unified Search ๐: Query multiple academic sources with a single interface.
- Download PDFs ๐ฅ: Download papers (when available) from supported sources.
- Read Papers ๐: Extract and return text from downloaded PDFs (where supported).
- MCP Compatible ๐ค: Works as a local MCP tool for Claude, Open Interpreter, and other MCP clients.
- Extensible ๐ ๏ธ: Easily add new sources or tools.
Supported Sources ๐
- arXiv
- Zenodo
- bioRxiv
- medRxiv
- CrossRef
- Google Scholar
- ResearchGate
- Sci-Hub
- Elsevier (requires API key)
Quick Start ๐
You can run MCP Paper Finder in two ways:
1. Run with Docker (Recommended) ๐ณ
Copy this JSON as your MCP tool in your MCP client (Make sure to locate the config file). Feel free to add env variable in the env section. Env variables are presented in .env.example.
"mcpServers": {
"paper-finder": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"DOTENV_CONFIG_QUIET=true",
"walids35/mcp-paper-finder"
],
"env": {
"ELSEVIER_API_KEY": "your API KEY", // OPTIONAL (in case you want to use elsevier provider)
"RESEARCHGATE_COOKIE": "", // OPTIONAL (in case of 429 Too many requests error)
"SCIHUB_COOKIE": "" // OPTIONAL (recommended to bypass DDOS Guard)
}
}
}
2. Run Locally ๐ป
git clone https://github.com/Walids35/mcp-paper-finder.git
cd mcp-paper-finder
npm install
npm run build
- Create
.envfile and add the environment variables presented in.env.example
Then, add the path to your built entry point (e.g., node ./build/index.js) as a local tool in your MCP client (such as Claude or Open Interpreter).
"paper-finder": {
"command": "node",
"args": [
"ABSOLUTE/PATH/TO/MCPDIRECOTRY/build/index.js"
]
}
Testing ๐งช
Run all tests with:
npm test
Project Structure ๐๏ธ
src/
index.ts # MCP server entry point
providers/ # Source-specific search/download/read logic
tests/ # Jest test cases for each provider
types/ # Shared type definitions
Adding New Sources โ
- Implement a new provider class in
src/providers/. - Register it as a tool in
src/index.ts. - Add tests in
src/tests/.
Demo

License ๐
Note: This project is for research and educational purposes. Respect the terms of service and copyright policies of each data provider.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.