Deep Research

by joshualelon

6 stars

Not rated

GitHub

About

Integrates multiple AI agents to conduct in-depth research on complex topics with customizable tones, providing detailed progress reporting and error handling.

Details

Author: joshualelon
Repository: JoshuaLelon/deep-research-mcp
GitHub stars: 6
Categories: AI, Design, Developer Tools, Search, Frontend, Infrastructure

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name Deep Research

Command (node, npx, python, etc.) path/to/your/python/interpreter
Arguments
- Argument 1 /path/to/this/project/deep-research-mcp/mcp_server.py
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "deep research": {
            "cwd": null,
            "env": {},
            "args": [
                "/path/to/this/project/deep-research-mcp/mcp_server.py"
            ],
            "shell": false,
            "command": "path/to/your/python/interpreter"
        }
    }
}

JSON

{
    "mcpServers": {
        "deep research": {
            "cwd": null,
            "env": {},
            "args": [
                "/path/to/this/project/deep-research-mcp/mcp_server.py"
            ],
            "shell": false,
            "command": "path/to/your/python/interpreter"
        }
    }
}

JSON

{
    "mcpServers": {
        "deep research": {
            "cwd": null,
            "env": {},
            "args": [
                "/path/to/this/project/deep-research-mcp/mcp_server.py"
            ],
            "shell": false,
            "command": "path/to/your/python/interpreter"
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "deep research": {
            "cwd": null,
            "env": {},
            "args": [
                "/path/to/this/project/deep-research-mcp/mcp_server.py"
            ],
            "shell": false,
            "command": "path/to/your/python/interpreter"
        }
    }
}

JSON

{
    "mcpServers": {
        "deep research": {
            "cwd": null,
            "env": {},
            "args": [
                "/path/to/this/project/deep-research-mcp/mcp_server.py"
            ],
            "shell": false,
            "command": "path/to/your/python/interpreter"
        }
    }
}

JSON

{
    "mcpServers": {
        "deep research": {
            "cwd": null,
            "env": {},
            "args": [
                "/path/to/this/project/deep-research-mcp/mcp_server.py"
            ],
            "shell": false,
            "command": "path/to/your/python/interpreter"
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "deep research": {
            "cwd": null,
            "env": {},
            "args": [
                "/path/to/this/project/deep-research-mcp/mcp_server.py"
            ],
            "shell": false,
            "command": "path/to/your/python/interpreter"
        }
    }
}

JSON

{
    "mcpServers": {
        "deep research": {
            "cwd": null,
            "env": {},
            "args": [
                "/path/to/this/project/deep-research-mcp/mcp_server.py"
            ],
            "shell": false,
            "command": "path/to/your/python/interpreter"
        }
    }
}

JSON

{
    "mcpServers": {
        "deep research": {
            "cwd": null,
            "env": {},
            "args": [
                "/path/to/this/project/deep-research-mcp/mcp_server.py"
            ],
            "shell": false,
            "command": "path/to/your/python/interpreter"
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "deep research": {
            "cwd": null,
            "env": {},
            "args": [
                "/path/to/this/project/deep-research-mcp/mcp_server.py"
            ],
            "shell": false,
            "command": "path/to/your/python/interpreter"
        }
    }
}

JSON

{
    "mcpServers": {
        "deep research": {
            "cwd": null,
            "env": {},
            "args": [
                "/path/to/this/project/deep-research-mcp/mcp_server.py"
            ],
            "shell": false,
            "command": "path/to/your/python/interpreter"
        }
    }
}

JSON

{
    "mcpServers": {
        "deep research": {
            "cwd": null,
            "env": {},
            "args": [
                "/path/to/this/project/deep-research-mcp/mcp_server.py"
            ],
            "shell": false,
            "command": "path/to/your/python/interpreter"
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "deep research": {
            "cwd": null,
            "env": {},
            "args": [
                "/path/to/this/project/deep-research-mcp/mcp_server.py"
            ],
            "shell": false,
            "command": "path/to/your/python/interpreter"
        }
    }
}

JSON

{
    "mcpServers": {
        "deep research": {
            "cwd": null,
            "env": {},
            "args": [
                "/path/to/this/project/deep-research-mcp/mcp_server.py"
            ],
            "shell": false,
            "command": "path/to/your/python/interpreter"
        }
    }
}

JSON

{
    "mcpServers": {
        "deep research": {
            "cwd": null,
            "env": {},
            "args": [
                "/path/to/this/project/deep-research-mcp/mcp_server.py"
            ],
            "shell": false,
            "command": "path/to/your/python/interpreter"
        }
    }
}

From the repository

1. Clone the Repository:

   git clone https://github.com/yourusername/deep-research-mcp.git

   cd deep-research-mcp

2. Create/Populate Your .env File:

cp .env.example .env

3. Install Dependencies:

   pip install -r multi_agents/requirements.txt

4. Edit your claude_desktop_config.json file to include the following:

    {

        "mcpServers": {

            "deep-research-mcp": {

                "command": "path/to/your/python/interpreter",

                "args": [

                    "/path/to/this/project/deep-research-mcp/mcp_server.py"

                ]

            }

        }

    }

5. Run the MCP Server:

   python mcp_server.py

This starts the FastMCP tool server locally. From here, any MCP-compatible client or the CLI can invoke the deep_research tool.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "deep research": {
            "cwd": null,
            "env": {},
            "args": [
                "/path/to/this/project/deep-research-mcp/mcp_server.py"
            ],
            "shell": false,
            "command": "path/to/your/python/interpreter"
        }
    }
}

Linux

{
    "cwd": null,
    "env": [],
    "args": [
        "/path/to/this/project/deep-research-mcp/mcp_server.py"
    ],
    "shell": false,
    "command": "path/to/your/python/interpreter"
}

Macos

{
    "cwd": null,
    "env": [],
    "args": [
        "/path/to/this/project/deep-research-mcp/mcp_server.py"
    ],
    "shell": false,
    "command": "path/to/your/python/interpreter"
}

Windows

{
    "cwd": null,
    "env": [],
    "args": [
        "/path/to/this/project/deep-research-mcp/mcp_server.py"
    ],
    "shell": false,
    "command": "path/to/your/python/interpreter"
}

Deep Research MCP

This repository provides a multi-agent research framework using Python and MCP (Message Control Protocol). The default entrypoint is mcp_server.py, which sets up a FastMCP server named Deep Research and exposes a tool named deep_research.

Setup

1. Clone the Repository:

   git clone https://github.com/yourusername/deep-research-mcp.git

   cd deep-research-mcp

2. Create/Populate Your .env File:

   cp .env.example .env

   # Then edit the new .env file to fill in your secrets and environment variables

   # For example:

   # OPENAI_API_KEY=sk-123-yourkey

   # Additional environment variables can be placed here

3. Install Dependencies:

   pip install -r multi_agents/requirements.txt

4. Edit your claude_desktop_config.json file to include the following:

    {

        "mcpServers": {

            "deep-research-mcp": {

                "command": "path/to/your/python/interpreter",

                "args": [

                    "/path/to/this/project/deep-research-mcp/mcp_server.py"

                ]

            }

        }

    }

5. Run the MCP Server:

   python mcp_server.py

This starts the FastMCP tool server locally. From here, any MCP-compatible client or the CLI can invoke the deep_research tool.

Project Overview

- multi_agents
- agents: Contains the various AI agents (ResearchAgent, EditorAgent, etc.).
- memory: Typed dictionaries to store research and draft states.
- main.py: Core logic to load tasks and orchestrate agents.
- README.md: Additional instructions on usage, file output settings, etc.
- mcp_server.py: Main FastMCP server file (entrypoint).
- utils: Shared functions and enums used across the codebase.
- .gitignore, requirements.txt, etc.: Standard setup files.

Below is a copy of the multi_agents/README.md in a tree-like structure for reference:

multi_agents/
│
├─ README.md
│   └─ (Documentation on file output vs. direct return)
│
├─ agents/
│   ├─ __init__.py
│   ├─ browser.py
│   ├─ researcher.py
│   ├─ editor.py
│   ├─ writer.py
│   ├─ publisher.py
│   └─ ... (other agents)
│
├─ memory/
│   ├─ __init__.py
│   ├─ draft.py
│   └─ research.py
│
├─ main.py
├─ __init__.py
└─ requirements.txt

29:["$","div",null,{"className":"my-8 pb-8 h-full max-w-5xl mx-auto","children":["$","div",null,{"

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

Linux

Macos

Windows

Deep Research MCP

Setup

Project Overview

Install

More like this

Sentry

Github

Git

GitLab

Context 7

1Panel