Grill MCP server
Commit Nov 13, 2026Provides a second opinion from an independent AI model to challenge and stress-test your decisions before you commit to them.
Also known as mtangoz/grill
- Stars
- 1
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.1.0
- Last commit
- Nov 13, 2026
- License
- MIT
What is Grill MCP?
Grill provides a second opinion from an independent AI model to challenge and stress-test your decisions before you commit to them.
Summary generated from the project's README
About Grill MCP server
Grill provides an independent second opinion to stress-test decisions before they are finalized. It works by sending a decision to an outside judge, which is a model from a different company than the one you are currently using. This process helps identify weaknesses in a plan by providing a verdict, a critical question, and a suggested test to verify assumptions.
Users can connect Grill to various AI clients including Claude, ChatGPT, Copilot, DeepSeek, Gemini, Grok, or Muse. For a local setup with Claude Desktop or Claude Code, you can use an OpenRouter API key to access the model router. Other users can use copy-and-paste methods or custom connectors without needing an API key. The tool is designed so that only the specific write-up you approve is sent to the judge, ensuring your full conversation remains private.
What you can do with it
- 1Stress-test business decisionsAsk the AI to challenge a strategic plan to find hidden assumptions.
- 2Verify launch assumptionsRequest a cheap test to see if a proposed change will actually achieve the desired result.
- 3Get an external perspectiveUse a model from a different company to provide a neutral verdict on your current work.
Written from the project's README. Every use case is checked against a quote from it.
Configuration
GRILL_API_KEYSecretOpenRouter key. The server lists its tools without one. A grill needs it.
| Name | Description | |
|---|---|---|
| GRILL_API_KEY | OpenRouter key. The server lists its tools without one. A grill needs it. | Secret |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work
- Source repository linked and reachablemtangoz/grill is public and reachablegithub.com/mtangoz/grill ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-12github.com/mtangoz/grill ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubGrill: grill your AI before you send it to your boss
Hear the strongest case against your plan, then decide for yourself.
Setup guide: grillyour.ai No key needed: Anyone can sign up and connect Grill to the AI they use at https://grillyour.ai/mcp. See it first: four made-up decisions, grilled
Tell the assistant you think with, "grill this": Claude, ChatGPT, Copilot, DeepSeek, Gemini, Grok or Muse. It sends the decision as you said it. An outside judge, a model from a different company, comes back with a short note: one verdict line, then one short line naming the question that would change the call when the judge named one, then the sharpest point and one cheap test when the judge named one. The verdict, the point and the test stay within about 50 words. The extra line is at most about 25 words, and it never comes before the verdict. Say more, options, or your call when you want the rest. After that closing line, a two-line run note names the models that answered and how long it took, then one sentence on privacy. Never drop the run note. Never put it before the verdict. A thin line gets a quick take and one question, not a refusal. A record is written only after you answer, and a percent is optional. Grill does not store it on the installed tool.
Verdict: shaky. The plan assumes customers stay at the new price, and nothing in it tests that. Falsifier: show the new price to one in ten new signups for two weeks, and compare how many start paying.
What Grill promises
The verdict never becomes the decision. You decide. Your values and judgment calls are yours: each verdict lists what the judge checked for you separately from what is your call. The judge is a model from a different company. Grill uses OpenRouter's Auto Router, and it does not pin models. Only the write-up you approve leaves your machine. Every promise, and the code and test that enforce it: docs/PRINCIPLES.md.
Set up
Claude Desktop and Claude Code enforce that in code. The copy-and-paste routes check it and warn you. Who to paste into is in the table below.
When Grill is connected, most apps show a Grill tool call when it runs. If yours shows none and the answer still claims to be Grill's, Grill may not have run.
Grill in chat
Anyone can sign up. The steps are at grillyour.ai/start. Use the same email each time, the email you signed up with, every time.
- Claude.ai, verified working. Works on the web, the desktop app and the phone app. The free plan allows only one custom connector. On a Team plan, an owner adds Grill, then each person signs in to Grill themselves. Add Grill to Claude. Check the name says Grill and the URL says
https://grillyour.ai/mcp, then Add and Connect, and sign in. Link didn't open? Customize → Connectors → Add custom connector and pastehttps://grillyour.ai/mcp. Asking Claude in a chat to connect it does not work. - ChatGPT. On chatgpt.com, and in the desktop app where that is supported, in the same account or workspace where you add it. The iPhone and Android apps can't run custom connectors. Plugins → + → Add custom MCP server. Name Grill, server URL
https://grillyour.ai/mcp, choose OAuth. Tick I understand and want to continue, then Create, then Install, and sign in. - Grok Bot, verified working. Works on the desktop app and the phone app. Premium, Super and Ultra on The X Subscription include it. Check your X plan includes Grok Bot. Tell the bot
Add this MCP server: https://grillyour.ai/mcp, then sign in when asked. - Gemini: Copy and paste works today. No install, no key. The steps are under ChatGPT, Copilot, DeepSeek, Gemini, Grok or Muse. Adding Grill as a connector inside Gemini is not verified. You can try it. For now, a personal Google account, in the US, 18 or over, in English, with Keep Activity on. On gemini.google.com: Settings, Connected Apps, Add a custom app, paste
https://grillyour.ai/mcp, Next, then sign in. - Microsoft 365 Copilot. To connect Grill in Microsoft 365 Copilot, an admin has to add it first. Copy and paste works without that. Consumer Copilot's documented connectors don't include custom servers, so use copy and paste.
- Meta AI (Muse): Copy and paste works today. No install, no key. The same steps as Gemini, above. Adding Grill as a connector inside Muse is not verified. You can try the steps below. Not yet verified end to end.
Setup for the owner is in docs/HOSTED.md.
Claude Desktop (Mac or Windows): the one-click judge, about 2 minutes with a key, about 10 if you need one
- Get a key for Grill's model router: go to openrouter.ai/keys, sign in, click Create key, and add credit.
- Install Grill. Download grill.mcpb and double-click it, or drag it onto the Claude window. Paste your key when Claude asks. There's nothing else to install; Claude Desktop runs it.
- Try it. In any chat, type: Grill this: we're moving our launch to March. I'm 70% sure it gets us more signups.
The extension reads GRILL_API_KEY. OPENROUTER_API_KEY works when that is unset.
claude.ai on the web or your phone: no key needed
- Download grill-skill.zip. In Claude, open Customize → Skills, upload it, and switch it on.
To add everything at once instead, go to Customize → Plugins → Add → Add marketplace and enter
mtangoz/grill. - Say "grill this: …". Claude writes the judge's prompt. Tap Open in ChatGPT, or paste it into Gemini, then paste the answer back into Claude.
Want it in one step? Use Claude Desktop, above.
ChatGPT, Copilot, DeepSeek, Gemini, Grok or Muse: no install, no key
- Copy the Grill prompt into the assistant you think with, and say what you're deciding.
- It writes your decision up with you, then gives you a prompt for the judge.
- Paste that into an assistant from a different company, then paste the answer back.
| You think with | Judge with |
|---|---|
| ChatGPT | Claude, Gemini or Grok |
| Copilot | Gemini, because Copilot can run OpenAI, Anthropic or xAI models |
| DeepSeek | Claude, ChatGPT, Gemini or Grok |
| Gemini | Claude, ChatGPT or Grok |
| Grok or GrokBot | Claude, ChatGPT or Gemini |
| Muse | Claude, ChatGPT or Gemini |
Meta AI (Muse)
You can try these steps. Adding Grill as a connector inside Muse is not verified.
- In Muse, ask it to add a custom connector named Grill (Meta's help: custom connectors are created in chat; Settings → Connectors is for the built-in list).
- URL:
https://grillyour.ai/mcp. Transport: Streamable HTTP. Sign-in: OAuth. - If Muse asks for a Client ID, use
RNdHSHmWCRJO40vd. Same for everyone. No secret. - Tap Add, then sign in with the same email you signed up with, every time. We email you a code; check spam if it isn't there in a minute.
Cursor, VS Code, Codex, Gemini CLI, or any app that runs MCP servers
In Cursor, a desktop connection and a Cloud Agent connection are separate sign-ins. In Codex, check cloud authentication separately from the desktop app.
npx -y grillyour --set-key # once: paste your key, Enter, then Ctrl-D
Then add a server named grill that runs npx -y grillyour. The config holds no key. Each app's config, and one-click installs for Cursor and VS Code, are in docs/ANY-APP.md. A Grill Pro key works here too.
Claude Code
/plugin marketplace add mtangoz/grill
/plugin install grill@grill
It asks for your model router key. Grill reads GRILL_API_KEY first. OPENROUTER_API_KEY works when that is unset. Or save the key once for every app on this computer with npx -y grillyour --set-key. It goes in ~/.config/grill/key, outside any project's .env.
When Claude Code shows you a plan to approve, Grill adds one line, once a session: want an outside judge on this plan first? Keep planning and say "grill this plan". Claude Code hands the hook the plan, and the hook ignores it: it sends nothing and keeps nothing of the plan. To ask once, it keeps an empty marker file per session in the plugin's data folder, and removes markers older than two days the next time it runs. Turn it off with GRILL_PLAN_OFFER=off.
Claude Code's advisor (/advisor) has a stronger Claude look over the work. That is a second opinion from the same company. Grill's judge is from a different one. Use both.
What it costs
Grill is free. On your own key you pay the router. Copy and paste uses the assistants you already have.
Coming later: an optional Pro plan with saved decision history and look-back reminders. The free tool stays free and account-free. Hear when it's ready.
Privacy
- Your notes stay in your tools. Only the write-up you approve is sent. The reflection you write stays in your chat or your own notes.
- The free tool has no account. Grill's makers never see your decisions on that tool. Anonymous usage stats are off unless you turn them on. An in-chat account is open to anyone who signs up; what it stores is in docs/DATA-LEDGER.md.
- A key, token or password in the write-up stops the run. Email addresses, phone numbers, card and bank numbers, ID numbers, labelled dates of birth, street addresses, postcodes and IP addresses are masked. Names are not. The full list is in docs/PRIVACY.md.
- The quality check (Jev) is on by default and also sees the masked write-up. Say "skip the check" to skip it for one grill, or switch it off in Grill's settings. The website counts visits without cookies.
- Grill news line: after a finished grill, at most once a session, and only within 7 days of a release or on the first 3 days of a month, a line with a link to hear when an optional Pro plan is ready. Showing the line sends nothing. Hide it with the "Show Grill news" setting, or
GRILL_NEWS=off. It stops on its own. - Anonymous usage stats: off by default. One metadata ping to Grill's website after the first successful grill, and never again. Never the decision, the question, the verdict, or your key.
What we will and won't do with your data, and how we build: docs/PRINCIPLES.md.
Turn anonymous usage stats on
Leave them off and the tool does not call Grill. To opt in:
- Claude Desktop: in the install dialog, switch on "Send anonymous usage stats (optional)".
- Claude Code:
/plugin→ Configure options, the same switch. - stdio, npx or Docker: set
GRILL_USAGE_STATS=on.
Turn them off in the same place, or set GRILL_PING=off. DO_NOT_TRACK=1 also disables the ping. The paste route does not send it.
Details: docs/PRIVACY.md.
Weekly review
Optional, in Claude, when you keep your own decision log: docs/WEEKLY-REVIEW.md.
License
MIT. See LICENSE. The code that handles your decision stays MIT for good (docs/PRINCIPLES.md). The name and logo are not part of the license: TRADEMARKS.md.
Grill MCP questions
Does Grill store my private decisions?
No, Grill does not store decisions on the installed tool, and only the write-up you explicitly approve is sent from your machine.
Is there a cost to use Grill?
The tool itself is free, though if you use your own API key via the model router, you will pay the router for usage.