AnmoL11221/Research-MCP-Server
3.1
If you are the rightful owner of Research-MCP-Server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.
This project is an AI-powered research assistant platform that integrates with Model-Context Protocol (MCP) for seamless tool usage in AI hosts.
Tools
6
Resources
0
Prompts
0
Research Assistant API
AI-powered research assistant that searches academic papers across arXiv, PubMed, and Semantic Scholar. Provides summarization, synthesis, and Q&A capabilities through both HTTP API and MCP integration for Claude Desktop.
Features
- Search across multiple academic databases
- AI-powered text summarization
- Multi-paper synthesis
- Question answering over research papers
- Citation generation
- Redis caching
- Dual Mode: HTTP API + MCP Server for Claude Desktop
Quick Start
Local Setup
git clone <your-repo-url>
cd research-mcp-server
python3.11 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
Environment Variables
SEMANTIC_SCHOLAR_API_KEY=your_key_here # Optional
REDIS_URL=redis://localhost:6379 # Optional
PORT=8080 # For HTTP mode only
Usage
As MCP Server (Claude Desktop Integration)
- Update Claude Desktop Config (
~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"research-assistant": {
"command": "/Users/home/Desktop/research-mcp-server/.venv/bin/python3",
"args": ["/Users/home/Desktop/research-mcp-server/mcp_server.py"]
}
}
}
- Start MCP Server:
source .venv/bin/activate
python mcp_server.py
- Restart Claude Desktop and look for the research tools in your chat!
As HTTP API Server
source .venv/bin/activate
PORT=8080 python mcp_server.py
# OR
uvicorn mcp_server:app --host 0.0.0.0 --port 8080
API Endpoints
GET /- Service info and available endpointsGET /health- Health checkPOST /api/search- Search academic papersPOST /api/summarize- Summarize textPOST /api/search_and_summarize- Search and summarize papersPOST /api/synthesize- Combine multiple papersPOST /api/cite- Generate citationsPOST /api/qa- Answer questions based on papers
MCP Tools (Available in Claude)
search- Search academic paperssummarize- Summarize textsearch_and_summarize- Search and summarize paperssynthesize- Combine multiple paperscite- Generate citationsqa- Answer questions based on papers
Usage Examples
HTTP API
curl -X POST http://localhost:8080/api/search \
-H "Content-Type: application/json" \
-d '{"query": "machine learning", "max_results": 5}'
Claude Desktop
Just ask Claude: "Search for recent papers on machine learning and summarize them"
Requirements
- Python 3.11+ (required for MCP functionality)
- Virtual environment (recommended)
- Redis (optional, for caching)
Docker Deployment
docker build -t research-assistant .
docker run -p 8080:8080 -e PORT=8080 research-assistant
License
MIT License