# Grill (mcpb · grill.mcpb)

A second opinion from an unrelated AI model before you commit to a decision.

- Trust score: 58/100 (low)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- mcpb · `grill.mcpb`: 58/100 (this document), [markdown](https://verifymcp.io/servers/mtangoz-grill/https-github-com-mtangoz-grill-releases-download-v0-1-0-grill-mcpb.md), [page](https://verifymcp.io/servers/mtangoz-grill/https-github-com-mtangoz-grill-releases-download-v0-1-0-grill-mcpb)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/mtangoz/grill/releases/download/v0.1.0/grill.mcpb`
- Version: `0.1.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-18.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to mtangoz/grill).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 21 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 73/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 478 tokens (~239/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 70/100
  - Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "grill" implies "send" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Grill MCP server?

Grill ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. The MCP registry declares no SHA-256 for this bundle, so there is no published digest to check the download against.

- Download bundle: `https://github.com/mtangoz/grill/releases/download/v0.1.0/grill.mcpb`

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-18 (score 58, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-16 (score 57, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 56, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 55, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 50. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-10 (score 54, +3)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 43. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-04 (score 51, +3)

- [functional improvement] Stability: unverified → 0.23

### 2026-09-28 (score 48, +10)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 38)

First indexed and scored.

## MCP tools (2)

### `grill` (~358 tokens)

Grill a decision

Send a decision, plan or forecast to an outside AI judge: a model from a different company than Claude. It writes the strongest case for and against, names the cheapest test that would settle each challenge, and gives a verdict (holds, holds-with-conditions, weak or refuted). Before calling: write the subject, meaning the decision, the options, the reasons, the prediction and confidence exactly as the user gave them, and the strongest case against. Show it to the user, and call only after they approve, because it leaves their machine for a model router (zero-data-retention endpoints only). The Jev quality check is ON: Jev, a decision model from TypeSafe, also sees the masked write-up and the report, on a zero-retention endpoint. Tell the user that before they approve, and that they can skip it for this grill (pass quality_check: false) or switch it off in Grill's settings. Costs about a cent on the user's own key and usually takes 1–3 minutes. If the result is a job id, call grill_result with it.

Input parameters:

- `author` (string): Optional. The model family that wrote the subject, if not Claude, for example openai. That family is excluded from judging too.
- `quality_check` (boolean): Optional. false skips the Jev quality check for this grill only, when the user asks. It never turns on a check the user switched off in settings.
- `question` (string): Optional. One neutral question, at most 600 characters, that never names a preferred answer. For a forecast, ask whether the confidence is too high, too low or about right.
- `subject` (string, required): The approved challenge subject, in markdown.

### `grill_result` (~51 tokens)

Collect a grill that was still running

Collect the report of a grill that returned a job id. Waits up to 45 seconds; call again if it is still running.

Input parameters:

- `job_id` (string, required): The job id the grill tool returned.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/mtangoz-grill/https-github-com-mtangoz-grill-releases-download-v0-1-0-grill-mcpb#diagnostics

## Score history

- 2026-10-18: 58
- 2026-10-17: 57
- 2026-10-16: 57
- 2026-10-15: 56
- 2026-10-14: 56
- 2026-10-13: 55
- 2026-10-12: 55
- 2026-10-10: 54
- 2026-10-04: 51
- 2026-10-03: 48
- 2026-10-02: 48
- 2026-10-01: 48
- 2026-09-30: 48
- 2026-09-29: 48
- 2026-09-28: 48
- 2026-09-27: 38

## Common questions

### What is the Grill MCP server?

Grill is an MCP server listed in the public MCP registry as io.github.mtangoz/grill. A second opinion from an unrelated AI model before you commit to a decision. This page covers its MCPB bundle (https://github.com/mtangoz/grill/releases/download/v0.1.0/grill.mcpb).

### Is the Grill MCP server safe to use?

Grill scores 58 out of 100 on VerifyMCP. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Grill MCP server expose?

Grill exposes 2 tools: grill, grill_result. Their descriptions and schemas cost roughly 409 tokens of context every time the server is loaded.

### What licence is the Grill MCP server under?

Grill declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- Repository: https://github.com/mtangoz/grill
- Website: https://grillyour.ai/
- Changelog RSS feed: https://verifymcp.io/servers/mtangoz-grill/https-github-com-mtangoz-grill-releases-download-v0-1-0-grill-mcpb.xml
- Changelog JSON feed: https://verifymcp.io/servers/mtangoz-grill/https-github-com-mtangoz-grill-releases-download-v0-1-0-grill-mcpb.json
- HTML version of this page: https://verifymcp.io/servers/mtangoz-grill/https-github-com-mtangoz-grill-releases-download-v0-1-0-grill-mcpb