{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_9a3x65qns6t8","handle":"kontrol-freek-mcp","url":"https://wellknown.network/agents/kontrol-freek-mcp","links":{"self":"https://wellknown.network/agents/kontrol-freek-mcp/record.json","html":"https://wellknown.network/agents/kontrol-freek-mcp","markdown":"https://wellknown.network/agents/kontrol-freek-mcp/record.md","api":"https://wellknown.network/api/v1/agents/kontrol-freek-mcp","status":"https://wellknown.network/api/v1/agents/kontrol-freek-mcp/status","claim":"https://wellknown.network/agents/kontrol-freek-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/kontrol-freek-mcp/claim.json","badge":"https://wellknown.network/agents/kontrol-freek-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/kontrol-freek-mcp/history","tools":"https://wellknown.network/api/v1/agents/kontrol-freek-mcp/tools"},"ard":{"identifier":"urn:air::server:kontrol-freek-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"kontrol-freek-mcp","summary":"AI assumption firewall for MCP agents — intercepts risky decisions, detects contradictions, and gates human approval via Telegram or Slack.","description":"# Kontrol Freek — AI Assumption Firewall for MCP Agents\n\n[![PyPI](https://img.shields.io/pypi/v/kontrol-freek-mcp)](https://pypi.org/project/kontrol-freek-mcp/)\n[![Python](https://img.shields.io/pypi/pyversions/kontrol-freek-mcp)](https://pypi.org/project/kontrol-freek-mcp/)\n[![License: MIT](https://img.shields.io/badge/license-MIT-blue)](LICENSE)\n[![MCP](https://img.shields.io/badge/protocol-MCP-orange)](https://modelcontextprotocol.io)\n\n**Kontrol Freek** is an open-source [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server that acts as an **AI safety guardrail** for autonomous agents. It intercepts AI assumptions before they cause irreversible mistakes, verifies every decision against a persistent project log, detects contradictions, scores risk, and routes human approval requests through Telegram, Slack, or native MCP elicitation — all without blocking your workflow.\n\n> Gate every AI assumption. Keep humans in the loop. Prevent agentic mistakes before they happen.\n\n---\n\n## Why Kontrol Freek?\n\nAI agents and coding assistants make implicit assumptions constantly — about architecture choices, file locations, API designs, and deployment targets. Without a structured checkpoint, these assumptions silently accumulate into hard-to-reverse technical debt or outright mistakes.\n\n**Kontrol Freek solves the human-in-the-loop problem for MCP agents**: it sits between your AI agent and every risky decision, comparing new assumptions against your project's history, flagging contradictions, and routing approval requests to you — wherever you are.\n\nKontrol Freek adds a **decision firewall** between your AI agent and every risky action:\n\n```\nAI: \"I'll use PostgreSQL for this project\"   ← assumption\n         ↓\ncheck_assumption(\"Use PostgreSQL\", risk=\"medium\", category=\"architecture\")\n         ↓\nKontrol Freek: query past decisions → detect contradictions → score risk\n         ↓\n├─ Low risk + past approval match  → ✅ Auto-approve, continue\n├─ Medium risk / new dec…","publisher":null,"homepage":"https://github.com/berkbayri/kontrol-freek-mcp","repository":"https://github.com/berkbayri/kontrol-freek-mcp/issues","version":"1.2.1","license":null,"protocols":["mcp"],"tags":["agentic-ai","ai-agent","ai-governance","ai-guardrails","ai-safety","assumption-validation","decision-log","human-in-the-loop","llm","mcp","mcp-server","model-context-protocol","telegram"],"pricing":null,"endpoints":[{"url":"pypi:kontrol-freek-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"communication.sms-voice","name":"SMS & Voice","confidence":1,"provenance":"declared"},{"slug":"data.database","name":"Databases","confidence":0.814,"provenance":"derived"}],"categories":["communication","data"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"kontrol-freek-mcp","registry":"pypi","observedAt":"2026-10-28T08:28:09.185Z","publishedAt":"2026-04-11T11:08:03.659634Z","latestVersion":"1.2.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"kontrol-freek-mcp","url":"https://pypi.org/project/kontrol-freek-mcp/","firstSeenAt":"2026-09-09T22:23:44.266Z","fetchedAt":"2026-10-28T08:26:55.000Z","normalizedAt":"2026-10-28T08:26:55.000Z"}]},"firstSeenAt":"2026-09-09T22:23:44.266Z","updatedAt":"2026-10-28T08:28:09.185Z"}