GPT Researcher MCP Server

@assafelovic

Repository Homepage

Basic information

About GPT Researcher MCP Server

An autonomous agent that conducts deep research on any data using any LLM providers

#python #search #agent #automation #research #ai #mcp #webscraping #llms #mcp-server #deepresearch

GPT Researcher MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "gpt-researcher": {
      "command": "npx",
      "args": [
        "skills",
        "add",
        "assafelovic/gpt-researcher"
      ]
    }
  }
}

GPT Researcher MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is 🔎 GPT Researcher?

GPT Researcher is an open deep research agent designed for web and local research on any given task. It produces detailed, factual, unbiased research reports with citations and addresses misinformation, speed, determinism, and reliability. The server integrates with MCP clients like Claude to extend deep research capabilities.

How to use 🔎 GPT Researcher?

Install via pip (pip install gpt-researcher) or clone the repository, set OPENAI_API_KEY and TAVILY_API_KEY environment variables, then run python -m uvicorn main:app --reload. To use as a Claude Skill, run npx skills add assafelovic/gpt-researcher. For MCP integration, set RETRIEVER=tavily,mcp and pass mcp_configs to GPTResearcher.

Key features of 🔎 GPT Researcher

Generate detailed research reports using web and local documents.
Smart image scraping and AI-generated inline images.
Aggregate over 20 sources for objective conclusions.
Deep Research with tree-like exploration and concurrent processing.
JavaScript-enabled web scraping and memory/context maintenance.
Export reports to PDF, Word, and other formats.

Use cases of 🔎 GPT Researcher

Conduct objective research on any topic with cited sources.
Combine web search with local documents for tailored reports.
Integrate deep research into AI assistants like Claude.
Automate generation of long-form reports (>2,000 words) with inline visuals.

Frequently asked questions

What API keys are required?

You need `OPENAI_API_KEY` and `TAVILY_API_KEY`. For AI-generated images, also set `GOOGLE_API_KEY` and `IMAGE_GENERATION_ENABLED=true`. Optional keys are `LANGCHAIN_API_KEY` and `GITHUB_TOKEN` for MCP GitHub integration.

Can I use local or custom LLM models?

Yes, set `OPENAI_BASE_URL` to your custom API base URL (e.g., for local models or other providers). Deep Research uses models like `o3-mini` by default.

Does 🔎 GPT Researcher support MCP?

Yes, it supports MCP integration via the `RETRIEVER=tavily,mcp` environment variable. You can connect to data sources like GitHub repositories, databases, and custom APIs by providing `mcp_configs`.

How long does a deep research task take?

Deep Research takes approximately 5 minutes per research and costs about $0.4 per research using `o3-mini` with "high" reasoning effort, as stated in the documentation.

Can I research local documents?

Yes, set `DOC_PATH` to the folder containing your documents (PDF, plain text, CSV, Excel, Markdown, PowerPoint, Word) and select "My Documents" in the frontend or set `report_source` to "local" in the PIP package.

Comments

More AI & Agents MCP servers

FLORA

FLORA is a remote MCP server available at https://agents.flora.ai. The FLORA MCP lets users generate, organize, and iterate on visual assets — hero images, moodboards, lifestyle shots, promo graphics — directly from a co

OpenZiti / LLM-Gateway

openziti

NetFoundry LLM Gateway is an OpenAI-compatible API proxy that routes requests across multiple LLM providers using zero-trust networking. Zero trust LLM gateway. OpenAI-compatible proxy with semantic routing and load bala

AskOne: Live Q&A and Polls

phuryn

Run free live audience Q&A and polls from your agent: start an AskOne room, add and launch a poll, approve or hide questions and mark them answered, close the room, then read the questions as a FAQ draft and get the resu

GoBuy - Product Trust

gobuy-ai

GoBuy gives AI agents marketplace-evidence trust scores. One call returns a 0–100 Evidence Score with observed/missing signals, freshness, and product context. Tools: • check_product_trust — inspect one Amazon, Walmart,

WordPress MCP Server

miniOrange

miniOrange WordPress MCP Server turns a WordPress site into a Model Context Protocol server, so AI clients like Claude, ChatGPT, Cursor, Gemini and Windsurf can read and edit the site through chat instead of the admin da