MCP.Market

Verdict MCP server

by Dgotlieb·io.github.Dgotlieb/verdict-mcp·v0.1.0a4

Sandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history

A88/100grade A
What users say
No reviews yet
Be the first
Safety scan
A88/100

full report

Adoption
New

0 stars18 downloads/wk

Reviews

Write one

Nobody has reviewed Verdict yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Verdict tools (4, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • explain_failure

    Full traceback and output for one failing check from a previous `verify` run.

  • history

    When was this failure fingerprint first/last seen, and how many times?

  • run_checkswrite action

    Run lint/type checks ('ruff', 'mypy') in the sandbox; same verdict shape as `verify`.

  • verify

    Verify the current working-tree changes by running affected pytest tests in a sandbox.

Public scan report

scanner v0.1.10 · 2026-10-31 · same rubric, same numbers if you re-run it

no findings
  • Code scan18 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 63 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 88/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Verdict compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
88/100
higher than 75% of 48,255 servers
Tools
4
the typical server has 7
Tools that change things
25%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
18
more than 5% of 12,191 servers with a package

What its tools let an agent do: 3 read · 1 run or deploy

Install Verdict in Claude Code, Cursor or VS Code

claude mcp add verdict-mcp -- uvx verdict-mcp
Add to Cursor

What the publisher says

From the Verdict repository's README, as published. We do not edit it. Read it on GitHub

verdict

https://github.com/user-attachments/assets/62923912-98aa-4246-8bc8-4adf55ae3ff8

Structured, sandboxed verification feedback for coding agents.

An MCP server that replaces your agent's pytest shell-outs with something built for the agent inner loop: impact-selected tests, run in an isolated environment, returning compact typed verdicts instead of 40,000 tokens of raw runner output — with failure fingerprints that tell the agent whether a failure is its regression or was broken all along.

raw pytest dump:  ~40,000 tokens, unstructured, run un-sandboxed on your machine
verdict:              ~400 tokens, typed JSON, run in a rootless container, with memory

Why

The highest-frequency tool call in agentic coding is verification — and it's the least structured. Agents re-run whole suites when one module changed, burn context parsing ANSI-coded tracebacks, run arbitrary code directly on your machine, and routinely misdiagnose pre-existing breakage as their own regression (then "fix" code that wasn't broken). verdict fixes all four.

Tools

Every failure carries a fingerprint: a stable hash of the normalized failure signature (volatile tokens — addresses, tmp paths, ids, durations — collapsed). Same logical failure, same fingerprint, across runs and refactors. Fingerprints are what give verdict memory.

Quickstart

No install step needed — uvx fetches it on first use. (Or uv tool install verdict-mcp / pip install verdict-mcp for a permanent verdict-mcp command.)

Claude Code — .mcp.json in your project root:

{
  "mcpServers": {
    "verdict": {
      "command": "uvx",
      "args": ["verdict-mcp"],
      "env": { "VERDICT_PROJECT": "." }
    }
  }
}

Cursor — same shape in .cursor/mcp.json.

Optional verdict.toml in your repo root:

[project]
packages = ["your_package"]          # for impact selection (auto-guessed if omitted)

[runner]
image = "ghcr.io/you/yourproj-test"  # prebuilt env with your deps
setup_cmd = "pip install -e .[test]" # or install on the fly (runs with network; tests don't)
# prefer = "local"                   # escape hatch if you have no container runtime

[limits]
max_failures = 10

Try it without an agent:

cd examples/demo_project
VERDICT_PROJECT=. verdict-mcp   # then connect any MCP client, or use the MCP inspector

Sandbox posture (v0.1)

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Verdict: common questions

Is Verdict MCP server safe?
Yes, by our scan: it is graded A (88/100). Read the Verdict safety report
How do I install Verdict?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Verdict need an API key?
No secret keys are declared. It reads 1 setting from the environment.
Is Verdict maintained?
The last commit was 67 days ago (2026-08-29). The latest release is v0.1.0a4.
What can I use instead of Verdict?
Servers from other publishers that do the same job: Qase Test Management MCP server.
How does Verdict compare with other MCP servers?
safety score 88/100 (higher than 75% of 48,255 servers); tools 4 (the typical server has 7); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Verdict

Same job from other publishers: the closest match first, then the best rated.

  • Qase Test Management
    Official MCP server for Qase — manage test cases, runs, suites, defects via AI tools.
    A