Claude Deep Research MCP server

Extends research capabilities by providing unified access to web and academic information through DuckDuckGo and Semantic Scholar integrations, enabling multi-stage workflows for exploration, synthesis, and analysis with proper citations.
Back to servers
Setup instructions
Provider
mcherukara
Release date
Mar 19, 2025
Language
Python
Stats
6 stars

This MCP server enables Claude and other compatible AI assistants to perform comprehensive research by integrating web and academic search functionality. It allows AI models to access current information from multiple sources, follow relevant links, and deliver well-structured research results with proper citations.

Installation

Prerequisites

  • Python 3.8 or higher
  • pip or uv package manager

Setup Process

# Using pip
pip install mcp httpx beautifulsoup4

# Clone the repository
git clone https://github.com/yourusername/claude-deep-research.git

Configuration

The server works with default settings, but you can customize parameters in deep_research.py:

# Configuration
USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
MAX_CONTENT_SIZE = 8000  # Maximum characters in the final response
MAX_RESULTS = 3         # Maximum number of results to process

Usage

Running the Server

Modify your Claude desktop config and restart Claude:

On a Mac, edit the file at ~/Library/Application Support/Claude:

  "search-scholar": {
      "command": "<Path to Python>/python",
      "args": [
        "<Path to deep research>/deep_research.py"
      ]
    }

Research Capabilities

The deep_research tool accepts these parameters:

  • query (required): The research question or topic
  • sources (optional): Which sources to use: "web", "academic", or "both" (default)
  • num_results (optional): Number of sources to examine (default 2, max 3)

Example Prompts

Can you research the latest developments in quantum computing?

I need comprehensive information about climate change mitigation strategies. Use the deep_research tool to help me.

Research the history and cultural significance of origami using academic sources.

Research Process

The server guides Claude through a structured research process:

  1. Initial Exploration: Gathers information from multiple sources
  2. Preliminary Synthesis: Organizes findings with visualization
  3. Follow-up Research: Identifies and explores knowledge gaps
  4. Comprehensive Analysis: Integrates all information with visual elements
  5. Proper Citations: Formats references using APA style

Troubleshooting

Common Issues

  • Server Connection Failures: Verify the correct path to the server file
  • Search Errors: Try using more specific queries if results are limited
  • Web Access Issues: Ensure proper internet connectivity
  • Content Formatting: Large responses may be truncated to fit size limits

Checking Logs

# View logs when running directly
python deep_research.py 2> server.log

# View logs from Claude Desktop (macOS/Linux)
tail -f ~/Library/Logs/Claude/mcp-server-deepresearch.log

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "search-scholar" '{"command":"python","args":["deep_research.py"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "search-scholar": {
            "command": "python",
            "args": [
                "deep_research.py"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "search-scholar": {
            "command": "python",
            "args": [
                "deep_research.py"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later