MCPLow riskUnclaimed

verdict-mcp

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

Dgotliebdgotlieb/verdict-mcpUpdated Aug 25, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.Dgotlieb/verdict-mcp",
  "description": "Sandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history",
  "repository": {
    "url": "https://github.com/Dgotlieb/verdict-mcp",
    "source": "github"
  },
  "version": "0.1.0a4",
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "verdict-mcp",
      "version": "0.1.0a4",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "Path to the project to verify (defaults to cwd)",
          "name": "VERDICT_PROJECT"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—python
Installs—pypi:verdict-mcp@0.1.0a4
Runs install scripts—None
NetworkNoneNone
Needs credentialsNoneNone
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #10.1.0a4latestOct 7, 2026