MCPLow riskUnclaimed

mcp-audit

Free context-engineering audits for AI agents. BYOK Anthropic key. Top-3 findings per scan.

archonicsarchonics/mcp-auditUpdated Apr 25, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.archonics/mcp-audit",
  "description": "Free context-engineering audits for AI agents. BYOK Anthropic key. Top-3 findings per scan.",
  "repository": {
    "url": "https://github.com/archonics/mcp-audit",
    "source": "github"
  },
  "version": "0.1.4",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "@archonics/mcp-audit",
      "version": "0.1.4",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "Your Anthropic API key. Required — the audit engine calls Claude directly from your machine.",
          "isRequired": true,
          "format": "string",
          "isSecret": true,
          "name": "ANTHROPIC_API_KEY"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—node
Installs—npm:@archonics/mcp-audit@0.1.4
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. #10.1.4latestOct 7, 2026