Skip to main content
Glama

Deep Researcher Agent & MCP Server ๐Ÿ”๐Ÿง 

Python 3.10+ Agno MCP Streamlit License: MIT Maintainer

An autonomous multi-stage AI research workflow agent that searches the web, analyzes unstructured data, and compiles publication-quality technical reports. Features both a Streamlit Web UI and a native Model Context Protocol (MCP) server for integration with Claude Desktop and Cursor.

Developed and maintained by Sakshi Pandey (231FA04H01@gmail.com).


๐Ÿ—๏ธ Multi-Stage Pipeline Workflow

graph TD
    classDef inputNode fill:#1E293B,stroke:#38BDF8,stroke-width:2px,color:#F8FAFC;
    classDef stageNode fill:#0F172A,stroke:#818CF8,stroke-width:2px,color:#F8FAFC;
    classDef outputNode fill:#064E3B,stroke:#34D399,stroke-width:2px,color:#FFF;

    Topic["๐ŸŽฏ User Research Query / Topic"]:::inputNode

    subgraph AutonomousResearchPipeline ["๐Ÿ”„ Multi-Stage Agno Workflow Engine"]
        Topic --> Searcher["๐Ÿ” Searcher Agent<br/><i>(Scrapegraph AI & Web Extraction)</i>"]:::stageNode
        Searcher --> Analyst["๐Ÿ“Š Analyst Agent<br/><i>(Pattern synthesis & data normalization)</i>"]:::stageNode
        Analyst --> Writer["โœ๏ธ Writer Agent<br/><i>(Markdown synthesis with inline citations)</i>"]:::stageNode
    end

    subgraph ClientInterfaces ["๐Ÿ”Œ Delivery Channels"]
        Writer --> StreamlitUI["๐Ÿ’ป Streamlit Web UI<br/><i>(Interactive research exploration)</i>"]:::outputNode
        Writer --> MCPServer["๐Ÿ”Œ Native MCP Server<br/><i>(Direct tool in Claude Desktop & Cursor)</i>"]:::outputNode
    end

Related MCP server: research

๐ŸŒŸ Key Features

  • ๐Ÿ”„ Multi-Stage Orchestration: Dedicated sub-agents (Searcher, Analyst, Writer) collaborate sequentially to produce exhaustive, cited research reports.

  • ๐ŸŒ AI-Assisted Scraping: Extracts data from live web pages using Scrapegraph AI and Nebius AI models.

  • ๐Ÿ”Œ Native MCP Server: Exposes the deep research pipeline as an MCP tool directly accessible inside Claude Desktop, Cursor, or any MCP-compatible client.

  • ๐Ÿ’ป Multiple Interfaces: Run research workflows via Streamlit web app, direct command line script, or through the background MCP server.


๐Ÿ› ๏ธ Tech Stack


๐Ÿ“ Repository Structure

deep-researcher-agent-mcp/
โ”œโ”€โ”€ app.py                  # Streamlit web interface
โ”œโ”€โ”€ agents.py               # Core multi-stage agent pipeline (Searcher, Analyst, Writer)
โ”œโ”€โ”€ server.py               # Native Model Context Protocol (MCP) server
โ”œโ”€โ”€ assets/                 # Architecture graphics and demo assets
โ”œโ”€โ”€ pyproject.toml          # uv / pip dependency specifications
โ”œโ”€โ”€ .env.example            # API key template
โ”œโ”€โ”€ .gitignore              # Git ignore rules
โ””โ”€โ”€ LICENSE                 # MIT License

โšก Quick Start

1. Prerequisites

2. Installation

# Clone the repository
git clone https://github.com/blue007-arc/deep-researcher-agent-mcp.git
cd deep-researcher-agent-mcp

# Install dependencies with uv
uv sync

3. Environment Setup

cp .env.example .env

Add your API keys to .env:

NEBIUS_API_KEY=your_nebius_api_key_here
SGAI_API_KEY=your_scrapegraph_api_key_here

๐Ÿ’ป Running the Agent

Option 1: Web Interface (Streamlit)

uv run streamlit run app.py

Open http://localhost:8501 in your browser. Enter any topic (e.g. "State of Autonomous Coding Agents in 2025") and watch the multi-stage research flow stream in real-time.

Option 2: Command Line

uv run python agents.py

Option 3: Connect to Claude Desktop or Cursor (MCP)

Add the server configuration to your claude_desktop_config.json or .cursor/mcp.json:

{
  "mcpServers": {
    "deep_researcher": {
      "command": "python",
      "args": [
        "run",
        "server.py"
      ],
      "env": {
        "NEBIUS_API_KEY": "your_nebius_api_key_here",
        "SGAI_API_KEY": "your_scrapegraph_api_key_here"
      }
    }
  }
}

๐Ÿ‘ค Author & Maintainer

Sakshi Pandey


๐Ÿ“„ License

This project is licensed under the MIT License - see the LICENSE file for details.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables deep research tasks using a multi-agent architecture that integrates any LLM and MCP tools. Available via MCP stdio, streamable HTTP, and SSE transports.
    17
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Multi-purpose research MCP server integrating web search, deep research, web scraping, research methodology routing, and GPT Researcher report generation.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    An MCP-native document research agent that provides search, summarization, and citation tools for iterative multi-step research, ending in validated structured JSON reports.
    MIT
  • F
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to perform unified web research through a single MCP server, including search, page fetching, recursive crawling, document parsing, YouTube transcript extraction, and deep multi-query research.
    3
    -