# gatekeeper

> gatekeeper — runestone-labs-gatekeeper. Use this tool when you need to control and monitor AI agent access to external tools, enforcing policies and tracking interactions through a detailed audit trail. It allows, approves, or denies tool calls based on predefined rules, ensuring secure and compliant operations. Ideal for managing AI agent tool usage in regulated environments or sensitive applications.

Canonical page: https://skillsregistry.net/skills/runestone-labs-gatekeeper  
JSON: https://api.skillsregistry.net/v1/skills/runestone-labs-gatekeeper

## Description

Policy enforcement for AI agent tool calls — allow, approve, or deny with audit trail

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/Runestone-Labs/gatekeeper)

## 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": "runestone-labs-gatekeeper"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/runestone-labs-gatekeeper` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/runestone-labs-gatekeeper/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