Home / MCP / Deep Research MCP Server
Provides a multi-agent research framework using Python and MCP to orchestrate AI agents for research tasks.
Configuration
View docs{
"mcpServers": {
"deep_research_mcp": {
"command": "path/to/your/python/interpreter",
"args": [
"/path/to/this/project/deep-research-mcp/mcp_server.py"
]
}
}
}Deep Research MCP is an automated, multi-agent research framework that runs as a FastMCP server and exposes a dedicated tool named deep_research. It enables you to orchestrate AI agents for research tasks, draft outputs, and iterative collaboration through MCP clients or CLIs.
Use an MCP client or the CLI to invoke the deep_research tool exposed by the FastMCP server. You will interact with a single entry point that coordinates multiple agents to perform research tasks, generate drafts, and refine results within a structured memory of ongoing work.
Prerequisites and initial setup help you get started quickly.
Install Python and a compatible package manager on your machine.
Concrete steps you should follow to set up the server locally:
# 1) Clone the project
git clone https://github.com/yourusername/deep-research-mcp.git
cd deep-research-mcp
# 2) Create your environment file
cp .env.example .env
# Edit the new .env file to fill in your secrets and environment variables
# For example:
# OPENAI_API_KEY=sk-123-yourkey
# 3) Install dependencies
pip install -r multi_agents/requirements.txt
# 4) Prepare configuration for MCP (example entry shown in code block below)
# Edit claude_desktop_config.json to include the MCP server entry as shown in the snippetNext, configure the MCP server entry so your client can discover and start the deep_research tool. The server uses a stdio-based setup pointing to the Python interpreter and the mcp_server entry script.
{
"mcpServers": {
"deep_research_mcp": {
"name": "deep_research_mcp",
"type": "stdio",
"command": "path/to/your/python/interpreter",
"args": [
"/path/to/this/project/deep-research-mcp/mcp_server.py"
]
}
}
}Start the FastMCP server locally so clients can connect to the deep_research tool.
python mcp_server.pyExposed MCP tool that runs the deep research workflow by coordinating multiple agents to perform research tasks, draft outputs, and refine results.