SkillFoxx

GPT Researcher skill

An autonomous deep-research agent: gathers sources, verifies them and writes a report on any question

  • 30,652 ★ on the repository
  • Last commit
  • Apache-2.0
SkillEditors’ pick

Extended access

Why this level

  • Reaches the web and reads external sources
  • Sends requests to external LLM and search services
All reasons and checks

assafelovic/gpt-researcherAuthor:Assaf Elovic

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/gpt-researcher

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Reaches the web and reads external sources
  • Sends requests to external LLM and search services

This is third-party code. Review the repository files before installing.

What it does

GPT Researcher runs multi-step research on a topic: it plans sub-questions, searches and reads sources on the web or in your own data and assembles a report with citations. It works with several LLM providers and search retrievers, and can itself call external MCP servers as sources. You can install it as a Python package, run it in Docker with a web UI, or connect it to Codex over MCP through the bundled skill. Optionally reports get generated illustrations.

Who it is for. For analysts, marketers and product teams who need thorough reports with sources.

Good fit when

  • You need a topic overview backed by verifiable sources
  • You want the agent to do deep data gathering instead of manual search
  • You want to invoke research from Codex over MCP

Not a fit when

  • You have no access to an LLM provider and a search API
  • You need a quick one-off answer rather than a full report

Example request

Run deep research on this topic and give me a report with sources

Limitations

It needs keys for an LLM provider and a search retriever (OpenAI and Tavily by default), and some providers are unavailable from Russia without a VPN. Deep research spends tokens and time, and report quality depends on the chosen models and sources.

How to disable. Uninstall the package (pip uninstall gpt-researcher) or stop the docker compose containers; if connected over MCP, remove the entry from your client's config.

FAQ

Is OpenAI required?

No, several LLM providers and retrievers are supported, but they need to be configured with keys.

How do I connect it to an agent?

Run it as an MCP source and connect, or for Codex install the skill via npx skills add.

Discussion

No questions or reviews yet.

Skills
Official

A personal AI agent for the terminal with shell, Python, web and local models, one of the earliest agent CLIs

CLIExtended access4.5K

A Codex skill that hands tasks to web ChatGPT with project terminal access, saving Codex quota; modes from Medium to Pro.

SkillBroad access138
Official

Feynman — a terminal AI agent for scientific research: literature reviews, source checks, paper critique and comparing a paper with its code

CLIExtended access10.1K

One /research command builds a cited report with counter-arguments and scenarios in ten minutes, in 19 languages with Russian.

SkillExtended access615

A teaching terminal coding agent in Python, built as a "nanoGPT for agents": read it, take it apart and fork it

CLIBroad access1.9K
Needs a VPN

A desktop app with a local MCP server that lets ChatGPT work with files, commands, skills and other MCP servers

MCP serverBroad access394

Comparison with similar tools

Cards that share the main search query, and how they differ.

ToolOfficialAuthenticationRepository starsMain difference
GPT Researcher (this card)no30,652
CoexistAInonot required531a local research MCP server
Research Toolkitno314a skill that takes research from question to a report where every
GPT Researcher MCPyesAPI key378an MCP server for deep web research

README in short

The README describes GPT Researcher as an autonomous deep-research agent that gathers sources and writes reports on any topic or data with any LLM. It supports MCP configurations as sources, installation from PyPI, running in Docker with a frontend and generating illustrations in reports. The repo includes a skill for using it from Codex over MCP and a Codex plugin. Apache-2.0 licensed.

README badge

Original SKILL.md

---
name: gpt-researcher
description: Autonomous deep research from Codex via MCP
---

# GPT Researcher for Codex

Use GPT Researcher from Codex via MCP.

## When to use
- When you need gpt-researcher capabilities in your Codex workflow
- See https://github.com/assafelovic/gpt-researcher for full setup instructions

Report a problem