MCPLow riskUnclaimed

Edgehound

Writes adversarial test suites for AI-built code. Your agent's test engineer.

Energixeenergixe/edgehound-mcpUpdated Sep 17, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.Energixe/edgehound-mcp",
  "description": "Writes adversarial test suites for AI-built code. Your agent's test engineer.",
  "title": "Edgehound",
  "repository": {
    "url": "https://github.com/Energixe/edgehound-mcp",
    "source": "github"
  },
  "version": "1.1.0",
  "websiteUrl": "https://mcpize.com/mcp/gauntlet",
  "remotes": [
    {
      "type": "streamable-http",
      "url": "https://gauntlet.mcpize.run/mcp"
    }
  ]
}

Permissions

DeclaredDetected
Runs code—None
Installs—None
Runs install scripts—None
Networkgauntlet.mcpize.rungauntlet.mcpize.run
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. #11.1.0latestOct 7, 2026