# Squire (oci · ghcr.io/reidgoodbar/squire-mcp:0.6.5)

CLI-first remote runtimes for validation and offload tasks, exposed over MCP stdio.

- Trust score: 39/100 (low)
- Change this week: −6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- oci · `ghcr.io/reidgoodbar/squire-mcp:0.6.5`: 39/100 (this document), [markdown](https://verifymcp.io/servers/reidgoodbar-squire/ghcr-io-reidgoodbar-squire-mcp-0-6-5.md), [page](https://verifymcp.io/servers/reidgoodbar-squire/ghcr-io-reidgoodbar-squire-mcp-0-6-5)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/reidgoodbar/squire-mcp:0.6.5`
- 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 2026-08-03.

- **Supply Chain Security**: 0/100
  - Malware scan not yet available for this package.
  - CVE data not yet available for this package.
  - Install-script risk not yet assessed.
  - Dependency-health data not yet available.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 119 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1606 tokens (~100/item across 16 items; 16 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 2 categories.** Categories scored 0 because we could not verify them: 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

### Claude

```bash
claude mcp add reidgoodbar-squire -- docker run --rm -i ghcr.io/reidgoodbar/squire-mcp:0.6.5
```

### Codex

```bash
codex mcp add reidgoodbar-squire -- docker run --rm -i ghcr.io/reidgoodbar/squire-mcp:0.6.5
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "reidgoodbar-squire": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/reidgoodbar/squire-mcp:0.6.5"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  reidgoodbar-squire:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/reidgoodbar/squire-mcp:0.6.5"]
```

### Other

```json
{
  "mcpServers": {
    "reidgoodbar-squire": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/reidgoodbar/squire-mcp:0.6.5"
      ]
    }
  }
}
```

## 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.

### 2026-08-01 (score 39, −6)

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

### 2026-07-27 (score 45, +34)

- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: pass

### 2026-07-26 (score 11)

First indexed and scored.

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

## MCP tools (16)

### `help` (~54 tokens)

Squire Help

Show the top-level Squire command catalog or help for a specific command. This is the canonical discovery surface for humans and agents before choosing a command.

Input parameters:

- `command` (string): Optional command path, such as verify or quantum simulate.

### `whoami` (~30 tokens)

Squire WhoAmI

Return the current public or authenticated identity, trust tier, feature flags, token metadata, and server-side quotas.

### `verify` (~93 tokens)

Squire Verify

Run small inline snippets or staged scripts in fresh Linux containers across the supported target images.

Input parameters:

- `code` (string): Inline code snippet to verify.
- `file` (string): Path to a local script file to upload.
- `language` (string, required): Language to execute: bash, python, or node.
- `targets`: Target matrix as an array or CSV string.
- `timeout` (integer): Per-target timeout in seconds.

### `deps` (~86 tokens)

Squire Deps

Validate whether dependency manifests install in a clean environment. The CLI surface exists, but the public zero-egress service currently rejects deps jobs.

Input parameters:

- `file` (string, required): Path to the dependency manifest to upload.
- `language` (string, required): Dependency language: python or node.
- `targets`: Dependency targets as an array or CSV string.
- `timeout` (integer): Dependency install timeout in seconds.

### `sql` (~134 tokens)

Squire SQL

Run SQLite or Postgres schema, query, and migration validation in a fresh disposable database sandbox.

Input parameters:

- `dialect` (string, required): SQL dialect: sqlite or postgres-16.
- `explain` (boolean): Request an execution plan when the dialect supports it.
- `file` (string): Path to a SQL file containing statements to apply.
- `query` (string): Inline SQL query to execute after schema setup.
- `query_file` (string): Path to a query file to execute after schema setup.
- `schema` (string): Path to a schema file to apply before the query.
- `timeout` (integer): SQL timeout in seconds.

### `test` (~103 tokens)

Squire Test

Run small or medium test jobs in clean runtimes with a target matrix for Python, Node, or Bash.

Input parameters:

- `command` (string): Restricted test command such as pytest -q or npm test.
- `files` (array, required): Local file paths to stage for the test run.
- `language` (string, required): Test language: python, node, or bash.
- `targets`: Runtime targets as an array or CSV string.
- `timeout` (integer): Test timeout in seconds.

### `lint` (~109 tokens)

Squire Lint

Run fixed lint and static-analysis tools in a fresh toolchain so local environment drift does not affect the result.

Input parameters:

- `files` (array, required): Local file paths to stage for the lint run.
- `language` (string, required): Lint language: python, js, ts, or rust.
- `targets`: Lint targets as an array or CSV string.
- `timeout` (integer): Lint timeout in seconds.
- `tool` (string, required): Lint tool: ruff, eslint, or clippy.

### `audit` (~152 tokens)

Squire Audit

Run the supported security-focused audit surfaces against staged local files. On the public service this currently means secret scanning and local-config static analysis.

Input parameters:

- `config` (string): Static analysis config as a staged local file path.
- `files` (array): Local file paths to stage.
- `language` (string): Audit language. Dependency audit is currently disabled publicly.
- `paths` (array): Local directory paths to stage recursively.
- `secrets` (boolean): Run the built-in secret scanner.
- `static` (boolean): Run static analysis.
- `targets`: Audit targets as an array or CSV string.
- `timeout` (integer): Audit timeout in seconds.
- `tool` (string): Audit tool, such as semgrep.

### `build` (~106 tokens)

Squire Build

Run offline packaging and build sanity checks in clean environments and optionally pull the resulting artifacts back locally.

Input parameters:

- `download_artifacts_dir` (string): Optional local directory to download build artifacts into.
- `files` (array): Local file paths to stage.
- `language` (string, required): Build language: python or node.
- `paths` (array): Local directory paths to stage recursively.
- `targets`: Build targets as an array or CSV string.
- `timeout` (integer): Build timeout in seconds.

### `bench` (~109 tokens)

Squire Bench

Run small, short-lived benchmark jobs in clean runtimes to compare simple timing behavior without turning Squire into a full performance platform.

Input parameters:

- `files` (array): Local file paths to stage.
- `iterations` (integer): Number of benchmark iterations.
- `language` (string, required): Benchmark language: python, bash, or go.
- `paths` (array): Local directory paths to stage recursively.
- `targets`: Benchmark targets as an array or CSV string.
- `timeout` (integer): Benchmark timeout in seconds.

### `browser` (~141 tokens)

Squire Browser

Run headless Chromium in a constrained offline sandbox and optionally download screenshots or other generated browser artifacts locally.

Input parameters:

- `browser` (string): Browser engine, currently chromium.
- `download_artifacts_dir` (string): Optional local directory to download screenshots or other browser artifacts into.
- `files` (array): Local file paths to stage.
- `paths` (array): Local directory paths to stage recursively.
- `screenshot` (string): Optional screenshot filename to produce.
- `script` (string): Path to a browser automation script to stage.
- `timeout` (integer): Browser timeout in seconds.
- `url` (string): Offline URL to open, such as a file:// URL.

### `compile` (~82 tokens)

Squire Compile

Run target-specific Go or Rust compilation checks in clean toolchains without turning Squire into a full CI or release system.

Input parameters:

- `files` (array, required): Local file paths to stage for compilation.
- `language` (string, required): Compile language: go or rust.
- `targets`: Compile targets as an array or CSV string.
- `timeout` (integer): Compile timeout in seconds.

### `solve` (~79 tokens)

Squire Solve

Run bounded solver jobs for Z3 or MiniZinc in a fresh disposable sandbox.

Input parameters:

- `data` (string): Optional MiniZinc .dzn data file.
- `file` (string, required): Path to the solver input file.
- `solver` (string, required): Solver: z3 or minizinc.
- `timeout` (integer): Solver timeout in seconds.

### `quantum_simulate` (~120 tokens)

Squire Quantum Simulate

Stage a small Python/Qiskit file set, run the entry file inside an offline Qiskit Aer image, and optionally download generated artifacts locally.

Input parameters:

- `backend` (string): Quantum backend. v1 supports only aer_simulator.
- `download_artifacts_dir` (string): Optional local directory to download generated quantum artifacts into.
- `files` (array, required): Local file paths to stage. The first file is the Python entry script.
- `shots` (integer): Shot count passed to the simulation.
- `timeout` (integer): Simulation timeout in seconds.

### `data` (~104 tokens)

Squire Data

Run Python data-processing jobs in a disposable remote runtime with pandas, polars, and pyarrow available.

Input parameters:

- `download_artifacts_dir` (string): Optional local directory to download generated data artifacts into.
- `input` (string): Path to an input file for multipart upload.
- `script` (string, required): Path to the Python script to execute.
- `stdin_text` (string): Small inline input payload to send over stdin mode.
- `timeout` (integer): Job timeout in seconds.

### `media` (~104 tokens)

Squire Media

Run Python media jobs in a disposable remote runtime with ffmpeg installed and optionally download the generated files locally.

Input parameters:

- `download_artifacts_dir` (string): Optional local directory to download generated media artifacts into.
- `input` (string): Path to an input file for multipart upload.
- `script` (string, required): Path to the Python script to execute.
- `stdin_text` (string): Small inline input payload to send over stdin mode.
- `timeout` (integer): Job timeout in seconds.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/reidgoodbar-squire/ghcr-io-reidgoodbar-squire-mcp-0-6-5#diagnostics

## Score history

- 2026-08-03: 39
- 2026-08-02: 39
- 2026-08-01: 39
- 2026-07-31: 45
- 2026-07-29: 45
- 2026-07-28: 45
- 2026-07-27: 45
- 2026-07-26: 11

## Links

- Repository: https://github.com/reidgoodbar/squire
- Changelog RSS feed: https://verifymcp.io/servers/reidgoodbar-squire/ghcr-io-reidgoodbar-squire-mcp-0-6-5/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/reidgoodbar-squire/ghcr-io-reidgoodbar-squire-mcp-0-6-5/changelog.json
- HTML version of this page: https://verifymcp.io/servers/reidgoodbar-squire/ghcr-io-reidgoodbar-squire-mcp-0-6-5