What it does

Judgment calls on small, cheap models: yes/no, pick-one and rate questions about any text, answered YES, NO or UNSURE. Runs on TypeSafe's Jev, open models on Ollaya, Ollama or a local NLI model; each judges up to 1,000 texts per call.

Local connectionPricing not confirmedv0.8.2

Connection manifest

Public connection metadata from the source. Follow the provider’s setup guide for authentication, permissions, and required variables.

{
  "name": "io.github.Kungie/gut",
  "version": "0.8.2",
  "repository": {
    "url": "https://github.com/Kungie/gut"
  },
  "remotes": [],
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "gutfeel-mcp",
      "version": "0.8.2",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "name": "TYPESAFE_API_KEY",
          "isRequired": false
        },
        {
          "name": "GUT_BACKEND",
          "isRequired": false
        },
        {
          "name": "GUT_MODEL",
          "isRequired": false
        },
        {
          "name": "GUT_BASE_URL",
          "isRequired": false
        },
        {
          "name": "OPENROUTER_API_KEY",
          "isRequired": false
        }
      ]
    }
  ]
}

Metadata reviewed for listing. Server code, permissions, and runtime behavior have not been security-audited. Directory access is free; individual providers may charge.