MCPLow riskUnclaimed

Vigilis

Gate AI-written tests: heal safe drift, refuse to hide real bugs, sign a verifiable receipt.

piyushpathakqapiyushpathakqa/vigilis-mcp★ 5Updated Jul 7, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.piyushpathakqa/vigilis-mcp",
  "description": "Gate AI-written tests: heal safe drift, refuse to hide real bugs, sign a verifiable receipt.",
  "title": "Vigilis",
  "repository": {
    "url": "https://github.com/piyushpathakqa/Vigilis",
    "source": "github"
  },
  "version": "0.4.1",
  "websiteUrl": "https://vigilis.dev",
  "packages": [
    {
      "registryType": "npm",
      "registryBaseUrl": "https://registry.npmjs.org",
      "identifier": "vigilis-mcp",
      "version": "0.4.1",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "Pay-as-you-go Anthropic API key used to run the Vigilis agent (not a Claude.ai subscription).",
          "isRequired": true,
          "isSecret": true,
          "name": "ANTHROPIC_API_KEY"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—node
Installs—npm:vigilis-mcp@0.4.1
Runs install scripts—None
NetworkNoneNone
Needs credentialsANTHROPIC_API_KEYANTHROPIC_API_KEY
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. #10.4.1latestOct 7, 2026