Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Squire

OCI · GHCR.IO/REIDGOODBAR/SQUIRE-MCP:0.6.5 · SCANNED SEP 20

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

0 this week 53 Trust /100
Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security0
  • Malware scan not yet available for this package.Unverified
  • Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
  • Install-script risk not yet assessed.Unverified
  • Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
Provenance & Transparency45
Schema Quality & AI Usability77
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1606 tokens (~100/item across 16 items; 16 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass

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 Squire MCP server?

Squire runs locally as a container image, launched with docker run --rm -i ghcr.io/reidgoodbar/squire-mcp:0.6.5. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

oci · ghcr.io/reidgoodbar/squire-mcp:0.6.5

# add to Claude Code
claude mcp add reidgoodbar-squire -- docker run --rm -i ghcr.io/reidgoodbar/squire-mcp:0.6.5
// .cursor/mcp.json
{
  "mcpServers": {
    "reidgoodbar-squire": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/reidgoodbar/squire-mcp:0.6.5"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "reidgoodbar-squire": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/reidgoodbar/squire-mcp:0.6.5"
      ]
    }
  }
}
# add to Codex CLI
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/config.yaml
mcp_servers:
  reidgoodbar-squire:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/reidgoodbar/squire-mcp:0.6.5"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "reidgoodbar-squire": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/reidgoodbar/squire-mcp:0.6.5"
      ]
    }
  }
}
// mcp.json
{
  "mcpServers": {
    "reidgoodbar-squire": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/reidgoodbar/squire-mcp:0.6.5"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 −3
    • Security disclosure: unverified → fail functional
    • Stability: pass → 0.80 functional
  • 17 Sept 26 +1
    • Stability: 0.97 → pass security
    • Security disclosure: fail → unverified functional
  • 15 Sept 26 +1
    • Security disclosure: unverified → fail functional
  • 13 Sept 26 +1
    • Security disclosure: fail → unverified functional
  • 10 Sept 26 −3
    • Stability: pass → 0.77 functional
  • 9 Sept 26 +1
    • Stability: 0.97 → pass security
  • 7 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed oci/ghcr.io/reidgoodbar/squire-mcp:0.6.5

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem oci
Reason No attestation published

Background: How many MCP packages publish verified provenance →

MCP tools · 16 exposed · ~1,606 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
audit ~152

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.

NameTypeReqDescription
configstringStatic analysis config as a staged local file path.
filesarrayLocal file paths to stage.
languagestringAudit language. Dependency audit is currently disabled publicly.
pathsarrayLocal directory paths to stage recursively.
secretsbooleanRun the built-in secret scanner.
staticbooleanRun static analysis.
targetsAudit targets as an array or CSV string.
timeoutintegerAudit timeout in seconds.
toolstringAudit tool, such as semgrep.

No output schema declared.

No examples provided.

bench ~109

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

NameTypeReqDescription
filesarrayLocal file paths to stage.
iterationsintegerNumber of benchmark iterations.
languagestringyesBenchmark language: python, bash, or go.
pathsarrayLocal directory paths to stage recursively.
targetsBenchmark targets as an array or CSV string.
timeoutintegerBenchmark timeout in seconds.

No output schema declared.

No examples provided.

browser ~141

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

NameTypeReqDescription
browserstringBrowser engine, currently chromium.
download_artifacts_dirstringOptional local directory to download screenshots or other browser artifacts into.
filesarrayLocal file paths to stage.
pathsarrayLocal directory paths to stage recursively.
screenshotstringOptional screenshot filename to produce.
scriptstringPath to a browser automation script to stage.
timeoutintegerBrowser timeout in seconds.
urlstringOffline URL to open, such as a file:// URL.

No output schema declared.

No examples provided.

build ~106

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

NameTypeReqDescription
download_artifacts_dirstringOptional local directory to download build artifacts into.
filesarrayLocal file paths to stage.
languagestringyesBuild language: python or node.
pathsarrayLocal directory paths to stage recursively.
targetsBuild targets as an array or CSV string.
timeoutintegerBuild timeout in seconds.

No output schema declared.

No examples provided.

compile ~82

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

NameTypeReqDescription
filesarrayyesLocal file paths to stage for compilation.
languagestringyesCompile language: go or rust.
targetsCompile targets as an array or CSV string.
timeoutintegerCompile timeout in seconds.

No output schema declared.

No examples provided.

data ~104

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

NameTypeReqDescription
download_artifacts_dirstringOptional local directory to download generated data artifacts into.
inputstringPath to an input file for multipart upload.
scriptstringyesPath to the Python script to execute.
stdin_textstringSmall inline input payload to send over stdin mode.
timeoutintegerJob timeout in seconds.

No output schema declared.

No examples provided.

deps ~86

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

NameTypeReqDescription
filestringyesPath to the dependency manifest to upload.
languagestringyesDependency language: python or node.
targetsDependency targets as an array or CSV string.
timeoutintegerDependency install timeout in seconds.

No output schema declared.

No examples provided.

help ~54

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.

NameTypeReqDescription
commandstringOptional command path, such as verify or quantum simulate.

No output schema declared.

No examples provided.

lint ~109

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

NameTypeReqDescription
filesarrayyesLocal file paths to stage for the lint run.
languagestringyesLint language: python, js, ts, or rust.
targetsLint targets as an array or CSV string.
timeoutintegerLint timeout in seconds.
toolstringyesLint tool: ruff, eslint, or clippy.

No output schema declared.

No examples provided.

media ~104

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

NameTypeReqDescription
download_artifacts_dirstringOptional local directory to download generated media artifacts into.
inputstringPath to an input file for multipart upload.
scriptstringyesPath to the Python script to execute.
stdin_textstringSmall inline input payload to send over stdin mode.
timeoutintegerJob timeout in seconds.

No output schema declared.

No examples provided.

quantum_simulate ~120

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

NameTypeReqDescription
backendstringQuantum backend. v1 supports only aer_simulator.
download_artifacts_dirstringOptional local directory to download generated quantum artifacts into.
filesarrayyesLocal file paths to stage. The first file is the Python entry script.
shotsintegerShot count passed to the simulation.
timeoutintegerSimulation timeout in seconds.

No output schema declared.

No examples provided.

solve ~79

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

NameTypeReqDescription
datastringOptional MiniZinc .dzn data file.
filestringyesPath to the solver input file.
solverstringyesSolver: z3 or minizinc.
timeoutintegerSolver timeout in seconds.

No output schema declared.

No examples provided.

sql ~134

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

NameTypeReqDescription
dialectstringyesSQL dialect: sqlite or postgres-16.
explainbooleanRequest an execution plan when the dialect supports it.
filestringPath to a SQL file containing statements to apply.
querystringInline SQL query to execute after schema setup.
query_filestringPath to a query file to execute after schema setup.
schemastringPath to a schema file to apply before the query.
timeoutintegerSQL timeout in seconds.

No output schema declared.

No examples provided.

test ~103

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

NameTypeReqDescription
commandstringRestricted test command such as pytest -q or npm test.
filesarrayyesLocal file paths to stage for the test run.
languagestringyesTest language: python, node, or bash.
targetsRuntime targets as an array or CSV string.
timeoutintegerTest timeout in seconds.

No output schema declared.

No examples provided.

verify ~93

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

NameTypeReqDescription
codestringInline code snippet to verify.
filestringPath to a local script file to upload.
languagestringyesLanguage to execute: bash, python, or node.
targetsTarget matrix as an array or CSV string.
timeoutintegerPer-target timeout in seconds.

No output schema declared.

No examples provided.

whoami ~30

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Common questions

What is the Squire MCP server?

Squire is an MCP server listed in the public MCP registry as io.github.reidgoodbar/squire. CLI-first remote runtimes for validation and offload tasks, exposed over MCP stdio. This page covers its container image (ghcr.io/reidgoodbar/squire-mcp:0.6.5).

Is the Squire MCP server safe to use?

Squire scores 53 out of 100 on VerifyMCP. 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 Squire MCP server expose?

Squire exposes 16 tools: help, whoami, verify, deps, sql, and 11 more. Their descriptions and schemas cost roughly 1,606 tokens of context every time the server is loaded.

Is the Squire MCP server still maintained?

Squire is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Squire MCP server under?

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