MCP Research Server
Provides tools for searching and retrieving research papers from arXiv, with capabilities to query papers by topic, extract detailed paper information, and automatically save paper metadata to local storage.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Research Server search for recent papers about quantum computing"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Research Assistant 🧠
A comprehensive Model Context Protocol (MCP) setup that provides powerful tools for research, file management, and web content fetching. This project integrates multiple MCP servers to enhance your AI assistant capabilities.
✨ Features
📚 Research Tool: Search and manage academic papers from arXiv
📁 Filesystem Tool: Browse, read, and manage project files
🌐 Fetch Tool: Retrieve content from websites and APIs
🤖 Multi-LLM Support: Works with Claude, Gemini, and other AI models
💾 Local Storage: Automatically saves research data organized by topics
Related MCP server: arXiv MCP Server
🛠️ Prerequisites
Python 3.13 or higher
uvpackage manager (recommended) orpipAPI keys for your chosen LLM providers
Claude Desktop (for MCP integration)
💻 Quick Start
1. Clone and Setup
git clone <your-repo-url>
cd mcp_project2. Install Dependencies
# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh
# Create virtual environment and install dependencies
uv sync3. Configure Environment Variables
Create a .env file in your project root:
ANTHROPIC_API_KEY=your_anthropic_api_key_here4. Configure Claude Desktop
Create or update your Claude Desktop configuration file:
Location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"."
],
"cwd": "/path/to/your/mcp_project"
},
"research": {
"command": "/path/to/your/mcp_project/.venv/bin/python",
"args": [
"/path/to/your/mcp_project/research_server.py"
],
"cwd": "/path/to/your/mcp_project"
},
"fetch": {
"command": "/path/to/your/.local/bin/uvx",
"args": ["mcp-server-fetch"],
"cwd": "/path/to/your/mcp_project"
}
}
}Important: Replace /path/to/your/mcp_project with your actual project path.
5. Restart Claude Desktop
Restart Claude Desktop completely to load the new configuration.
🎯 How to Use
Research Tool 🔬
Search for Papers:
Search for 5 papers about machine learningGet Paper Details:
Show me information about paper ID 1234.5678Browse Saved Papers:
What papers do I have saved on physics?Filesystem Tool 📁
Browse Files:
List all files in my project directoryRead Files:
Show me the contents of research_server.pyCreate Files:
Create a new Python script for data analysisFetch Tool 🌐
Get Web Content:
Fetch the latest Python documentationAPI Calls:
Get current weather data from an API📋 Available Tools
Research Server Tools
Tool | Description | Parameters |
| Search arXiv for papers |
|
| Get paper details |
|
| List saved topics | None |
Filesystem Server Tools
Tool | Description |
| Read file contents |
| Write to files |
| List directory contents |
| Delete files |
Fetch Server Tools
Tool | Description |
| Fetch content from URLs |
📁 Project Structure
mcp_project/
├── research_server.py # Main research MCP server
├── mcp_chatbot_L7.py # Chatbot with LLM integration
├── pyproject.toml # Project configuration
├── requirements.txt # Python dependencies
├── uv.lock # Dependency lock file
├── papers/ # Research data storage
│ └── [topic_name]/ # Organized by topic
│ └── papers_info.json # Paper metadata
├── .env # Environment variables
└── README.md # This file🔧 Configuration Details
Research Server Configuration
The research server automatically:
Creates topic-based directories in
papers/Saves paper metadata as JSON files
Provides search and retrieval functions
Integrates with arXiv API
Filesystem Server Configuration
The filesystem server:
Operates within your project directory
Provides full file management capabilities
Uses relative paths for portability
Fetch Server Configuration
The fetch server:
Handles web requests and API calls
Supports custom user agents
Can ignore robots.txt restrictions

Screenshot showing the MCP Research Assistant successfully running with all tools working
📝 Development
Adding New Tools
Edit
research_server.pyto add new functionsUse the
@mcp.tool()decoratorTest with MCP Inspector
Update documentation
Customizing LLM Behavior
Edit
mcp_chatbot_L7.pyModify tool descriptions and parameters
Add custom prompts and resources
Available Tools
2 toolsextract_infoA
Search for information about a specific paper across all topic directories.
Args: paper_id: The ID of the paper to look for
Returns: JSON string with paper information if found, error message if not found
Inputs: paper_id (required). Returns: result
search_papersA
Search for papers on arXiv based on a topic and store their information.
Args: topic: The topic to search for max_results: Maximum number of results to retrieve (default: 5)
Returns: List of paper IDs found in the search
Inputs: topic (required), max_results. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: extract_info retrieves information about a specific paper by ID, while search_papers finds papers on arXiv by topic and stores them. There is no overlap or ambiguity between these operations.
Both tools follow a consistent verb_noun pattern (extract_info and search_papers), using snake_case and descriptive action-object naming. The naming is predictable and readable throughout.
With only 2 tools for a research server, the set feels thin and incomplete for the apparent scope. A research domain typically requires more operations like managing papers, updating information, or handling citations, making this count inadequate.
There are significant gaps in the tool surface for a research server. While search and retrieval are covered, missing operations include creating, updating, or deleting paper records, organizing topics, or accessing stored data beyond extraction, which will limit agent workflows.
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
arXiv and OpenAlex/Crossref paper search (an open Google Scholar alternative) as agent tools.
Search arXiv/Semantic Scholar/OpenAlex + medical evidence (PubMed/Europe PMC) + LaTeX/PDF tools.
ArXiv preprint search, daily category digest, and author-collaborator graph.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that enables AI agents to search, retrieve, and analyze academic papers from arXiv, supporting features like keyword search, paper details retrieval, content extraction, and paper analysis.6MIT
- AlicenseAqualityDmaintenanceA Model Context Protocol server that enables natural language interaction with arXiv.org, allowing users to search, retrieve metadata, download PDFs, and load scholarly articles into LLM context.541MIT
- FlicenseNot gradedqualityDmaintenanceA Python implementation of the Model Context Protocol (MCP) server that enables searching and extracting information from arXiv papers, designed to be extensible with additional MCP tools.-
- AlicenseAqualityDmaintenanceEnables AI assistants to search, download, and access arXiv papers with local storage and date filtering via the Model Context Protocol.31Apache 2.0