drio
Open app

Deep Research MCP Server 🚀

Source

MCP Deep Research Server using Gemini creating a Research AI Agent

Catalog onlyCatalog onlySTDIO

Overview

Deep Research MCP is an AI-powered research assistant that utilizes Gemini to perform iterative, deep research on various topics by integrating search engines, web scraping, and large language models. It is designed to create a research AI agent that refines its research direction over time.

To use Deep Research MCP, you can either run it as an MCP tool for AI agents or use it standalone via the command line interface. For MCP, start the server and invoke it with a research query, depth, and breadth parameters. For standalone usage, run the CLI with your research query.

  • MCP Integration: Seamless integration with AI agents. - Iterative Research: Generates search queries and processes results iteratively. - Intelligent Query Generation: Uses Gemini LLMs for targeted search queries. - Depth & Breadth Control: Configurable parameters for research depth and breadth. - Comprehensive Reports: Produces detailed markdown reports with findings. - Persistent Knowledge: Utilizes PostgreSQL for storing research data.
  1. Conducting in-depth research on emerging technologies.
  2. Gathering comprehensive information for academic papers.
  3. Assisting AI agents in knowledge retrieval and processing.

Add to your AI client

Use these steps to connect Deep Research MCP Server 🚀 in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "deep-research-mcp-ssdeanx": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-deep-research-mcp-ssdeanx"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "deep-research-mcp-ssdeanx": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-deep-research-mcp-ssdeanx"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "deep-research-mcp-ssdeanx": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-deep-research-mcp-ssdeanx"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "deep-research-mcp-ssdeanx": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-deep-research-mcp-ssdeanx"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "deep-research-mcp-ssdeanx": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-deep-research-mcp-ssdeanx"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "deep-research-mcp-ssdeanx": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-deep-research-mcp-ssdeanx"
      ]
    }
  }
}

FAQ

Can Deep Research MCP handle all research topics?

Yes! It can research a wide range of topics by leveraging various data sources.

Is there a limit to the depth and breadth of research?

No, you can configure the depth and breadth parameters according to your needs.

How does it store research data?

It uses a PostgreSQL database to persistently store research findings and URLs.7:["$","div",null,{"className":"container mx-auto flex flex-col gap-4","children":["$L26","$L27",["$","$L28",null,{"currentProject":{"id":1281,"uuid":"882c268b-3020-4beb-bffa-74d2aa6feec0","name":"deep-research-mcp","title":"Deep Research MCP Server 🚀","description":"MCP Deep Research Server using Gemini creating a Research AI Agent","avatar_url":"https://avatars.githubusercontent.com/u/192780881?v=4","created_at":"2025-02-20T14:29:40.838Z","updated_at":"2025-02-23T07:21:19.305Z","status":"created","author_name":"ssdeanx","author_avatar_url":"https://avatars.githubusercontent.com/u/192780881?v=4","tags":"information-retrieval,research,knowledge,mcp,postgresql,gemini,postgresql-database,knowledge-base,autonomous-agents,ai-powered,research-automation,gemini-ai,mcp-servers,mcp-server,mcp-client,mcp-directory,deep-research,gemini-research,deep-research-google,research-automation-information-retrieval","category":"research-and-data","is_featured":false,"sort":1,"url":"https://github.com/ssdeanx/deep-research-mcp","target":"_self","content":"$29","summary":"$2a","img_url":"https://camo.githubusercontent.com/073448b87431cc89e91d32b765f75061f95c60b24bb83c52a47df150fa9b6e3e/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f4465657025323052657365617263682532304167656e742d4d43502532305365727665722d626c7565","type":null,"metadata":null,"user_uuid":null,"tools":null,"sse_url":null,"sse_provider":null,"sse_params":null,"is_official":false,"server_command":null,"server_params":null,"server_config":null,"allow_call":false,"is_innovation":false,"is_dxt":false,"dxt_manifest":null,"dxt_file_url":null,"is_audit":false},"randomProjects":[],"currentServerKey":"$undefined"}]]}]

Research and data