GPT Researcher for Codex via MCP
Plug the open-source GPT Researcher deep-research engine into Codex through MCP — autonomous web research with full setup on the project repo
- What
- Plug the open-source GPT Researcher deep-research engine into Codex through MCP — autonomous web research with full setup on the project repo
- Cost
- Free
- Needs
- the GPT Researcher backend set up (see the repo for full setup — the skill is a thin connector, not the engine); Codex with MCP support
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @assafelovic's skill for using GPT Researcher from Codex via MCP. GPT Researcher is the open-source autonomous deep-research engine (multi-agent web research with parallel search, synthesis and citations); this skill is the thin connector that brings its capabilities into a Codex workflow through the Model Context Protocol. Honest caveats: the skill file itself is very thin — it points to the main gpt-researcher repository for the full setup instructions (the real engine lives there, not in this skill); using it means running the GPT Researcher backend, which needs its own configuration and API keys. Apache-2.0 licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: the GPT Researcher backend set up (see the repo for full setup — the skill is a thin connector, not the engine); Codex with MCP support Install "GPT Researcher for Codex via MCP" for me. It gives my agent @assafelovic's connector for using the open-source GPT Researcher deep-research engine from Codex via MCP — autonomous web research (parallel search, synthesis, citations) available inside the Codex workflow. Apache-2.0 licensed. Note: the skill file is thin — follow the full setup instructions on the repository. Repository: https://github.com/assafelovic/gpt-researcher/blob/main/skills/gpt-researcher/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "gpt-researcher". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. set up the GPT Researcher backend per the repo instructions and save my API keys in the vault). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.