trackmcp
Back to directory
ragha02

Deep_rsrch_Gemini

View on GitHub

Multi Agent MCP - GEMINI Llm Setiup Deep Research Model

3 stars PythonAI & Machine Learning Updated Jul 23, 2025

Documentation

Agentic Deep Researcher

We're building an MCP-powered multi-agent deep researcher, it can perform deep web searches using Linkup amd the agents are orchestrated using CrewAI.

We use:

  • LinkUp (Search Tool)
  • CrewAI (Agentic design)
  • Gemini (LLM)
  • Streamlit to wrap the logic in an interactive UI

SetUp

Run these commands in project root

code
uv sync

Run the Application

Run the application with:

bash
streamlit run app.py

Use as MCP server

json
{
  "mcpServers": {
    "crew_research": {
      "command": "uv",
      "args": [
        "--directory",
        "./Multi-Agent-deep-researcher-mcp-windows-linux",
        "run",
        "server.py"
      ],
      "env": {
        "LINKUP_API_KEY": "your_linkup_api_key_here",
        "GEMINI_API_KEY": "your_gEMINI_API_KEY"
      }
    }
  }
}

Get your Linkup API keys here

Frequently asked questions

What is Deep_rsrch_Gemini?

Deep_rsrch_Gemini is Multi Agent MCP - GEMINI Llm Setiup Deep Research Model

How do I install Deep_rsrch_Gemini?

Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

Is Deep_rsrch_Gemini open source?

Yes — it is hosted on GitHub at https://github.com/ragha02/deep_rsrch_gemini and has 3 stars.

Related MCP tools

Run your own MCP server? See who uses it and what to fix.

Measure it with TrackMCP