-
securityA
license-
qualityEnables AI assistants to perform up-to-date web searches through the Tavily API, providing comprehensive search results with AI-generated summaries.
Last updated -
5
JavaScript
MIT License
The README references using Git to clone repositories for setup
The README references GitHub as the source for cloning the repository
The server produces detailed markdown reports with findings, sources, and reliability assessments
The README contains a Mermaid diagram to explain the workflow of the deep research process
The README mentions using a fork of Firecrawl that uses SearXNG as the search backend to avoid using a searchapi key
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
- Clone and install:
- Set up environment in
.env.local:
- Build:
- Run the cli version:
- 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
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
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:
- Set up local Firecrawl:
- 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
This server cannot be installed
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Enables iterative deep research by integrating AI agents with search engines, web scraping, and large language models for efficient data gathering and comprehensive reporting.
Related Resources
Related MCP Servers
- -securityFlicense-qualityA server that allows AI assistants to perform web searches using Perplexity's sonar-deep-research model with citation support.Last updated -2JavaScript
- AsecurityFlicenseAqualityA powerful research assistant that conducts intelligent, iterative research through web searches, analysis, and comprehensive report generation on any topic.Last updated -41TypeScript
- -securityAlicense-qualityEmpowers AI agents to perform web browsing, automation, and scraping tasks with minimal supervision using natural language instructions and Selenium.Last updated -1PythonApache 2.0