MCPLow riskUnclaimed

ThumbGate

Pre-action gates that block AI agents from repeating known mistakes.

IgorGanapolskyigorganapolsky/thumbgate★ 27Updated Jul 1, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.IgorGanapolsky/thumbgate",
  "description": "Pre-action gates that block AI agents from repeating known mistakes.",
  "title": "ThumbGate",
  "repository": {
    "url": "https://github.com/IgorGanapolsky/ThumbGate",
    "source": "github"
  },
  "version": "1.27.17",
  "websiteUrl": "https://thumbgate.ai",
  "packages": [
    {
      "registryType": "npm",
      "registryBaseUrl": "https://registry.npmjs.org",
      "identifier": "thumbgate",
      "version": "1.27.17",
      "transport": {
        "type": "stdio"
      }
    }
  ]
}

Permissions

DeclaredDetected
Runs code—node
Installs—npm:thumbgate@1.27.17
Runs install scripts—npm:thumbgate
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. #11.27.17latestOct 7, 2026