MCP Catalogs
Homegpt-researcher screenshot

gpt-researcher

by assafelovic·27,100·Score 61

An autonomous research agent that conducts deep research using any LLM providers with MCP server integration for specialized data sources.

ai-llmweb-scrapingproductivity
3,642
Forks
225
Open issues
1 mo ago
Last commit
2d ago
Indexed

Overview

GPT Researcher is a comprehensive autonomous agent designed for deep research on any given task. It produces detailed, factual, and unbiased research reports with citations, using both web and local document sources. The system implements a planner and execution architecture where the planner generates research questions while execution agents gather relevant information from over 20 sources. It features customizable agents, parallelized workflows for increased speed, and support for various document formats including PDF, Word, and Excel.

Try asking AI

After installing, here are 6 things you can ask your AI assistant:

you:Market research and competitive analysis
you:Academic literature review and synthesis
you:Technical documentation and research
you:Investigation and fact-checking
you:What is the difference between the main project and the MCP server?
you:What LLM providers can be used with GPT Researcher?

When to choose this

Choose this when you need a comprehensive research tool that can integrate with multiple data sources through MCP, especially for generating detailed reports with citations.

When NOT to choose this

Don't choose this if you need an actual MCP server that exposes tools/resources, rather than a client that consumes them, or if you need write access capabilities.

Comparable tools

gptr-mcpsemantic-search-mcpduckduckgo-mcpperplexity-apiserper-api

Installation

Installation

  1. Install Python 3.11 or later
  2. Clone the repository:

``bash git clone https://github.com/assafelovic/gpt-researcher.git cd gpt-researcher ``

  1. Set up API keys in .env file:

``bash export OPENAI_API_KEY={Your OpenAI API Key} export TAVILY_API_KEY={Your Tavily API Key} ``

  1. Install dependencies:

``bash pip install -r requirements.txt ``

  1. Run the server:

``bash python -m uvicorn main:app --reload ``

For MCP integration, see [gptr-mcp repository](https://github.com/assafelovic/gptr-mcp)

FAQ

What is the difference between the main project and the MCP server?
The main GPT Researcher project provides the full autonomous research agent with web interface and Python package, while the MCP server (gptr-mcp) is a dedicated repository specifically for MCP protocol integration, allowing other AI applications to connect to its research capabilities.
What LLM providers can be used with GPT Researcher?
GPT Researcher supports various LLM providers including OpenAI, and other OpenAI-compatible APIs. It can be configured with custom API base URLs to use local models or other providers.

Compare gpt-researcher with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.