# kontrol-freek-mcp

> kontrol-freek-mcp — berkbayri-kontrol-freek-mcp. Use this tool when you need to safeguard MCP agent decision-making by intercepting risky choices and ensuring human oversight. It solves problems of unchecked AI autonomy by detecting contradictions and gating approval through Telegram or Slack. Ideal for use cases requiring transparent and controlled AI decision-making, it takes in agent decisions and outputs gated approvals or contradictions.

Canonical page: https://skillsregistry.net/skills/berkbayri-kontrol-freek-mcp  
JSON: https://api.skillsregistry.net/v1/skills/berkbayri-kontrol-freek-mcp

## Description

AI assumption firewall for MCP agents — intercepts risky decisions, checks past decisions, detects contradictions, and gates human approval via Telegram or Slack.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** communication
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/berkbayri/kontrol-freek-mcp)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "berkbayri-kontrol-freek-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/berkbayri-kontrol-freek-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/berkbayri-kontrol-freek-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt