Deep Research MCP Server

Open Deep Research MCP Server

An AI-powered research assistant that performs deep, iterative research on any topic. It combines search engines, web scraping, and AI to explore topics in depth and generate comprehensive reports. Available as a Model Context Protocol (MCP) tool or standalone CLI. Look at exampleout.md to see what a report might look like.

Quick Start

1. Clone and install:

2. Set up environment in .env.local:

3. Build:

4. Run the cli version:

5. Test MCP Server with Claude Desktop:
   Follow the guide thats at the bottom of server quickstart to add the server to Claude Desktop:
   https://modelcontextprotocol.io/quickstart/server

For remote servers: Streamable HTTP

Server runs on http://localhost:3000/mcp without session management.

Features

• Performs deep, iterative research by generating targeted search queries
• Controls research scope with depth (how deep) and breadth (how wide) parameters
• Evaluates source reliability with detailed scoring (0-1) and reasoning
• Prioritizes high-reliability sources (≥0.7) and verifies less reliable information
• Generates follow-up questions to better understand research needs
• Produces detailed markdown reports with findings, sources, and reliability assessments
• Available as a Model Context Protocol (MCP) tool for AI agents
• For now MCP version doesn't ask follow up questions
• Natural-language source preferences (avoid listicles, forums, affiliate reviews, specific domains)

Model Selection (OpenAI, Anthropic, Google, xAI)

Pick a provider and model per run.

• CLI: you will be prompted for provider and model. Example: openai + gpt-5.
• MCP/HTTP: pass model, e.g. openai:gpt-5,

Set the corresponding API key in .env.local:

How It Works

Advanced Setup

Using Local Firecrawl (Free Option)

Instead of using the Firecrawl API, you can run a local instance. You can use the official repo or my fork which uses searXNG as the search backend to avoid using a searchapi key:

1. Set up local Firecrawl:

2. Update .env.local:

Optional: Observability

Add observability to track research flows, queries, and results using Langfuse:

The app works normally without observability if no Langfuse keys are provided.

License

MIT License