# agent-warden

> agent-warden — yli769227-jpg-agent-warden. Use this tool when you need to securely manage interactions between Claude Code and MCP servers, as it provides audit log management, policy enforcement, and secret scrubbing. It solves problems related to security and compliance by acting as a proxy, allowing for kill switch functionality in case of emergencies. Ideal for use cases requiring granular control over MCP server interactions, with inputs including git data and outputs comprising audited logs and enforced policies.

Canonical page: https://skillsregistry.net/skills/yli769227-jpg-agent-warden  
JSON: https://api.skillsregistry.net/v1/skills/yli769227-jpg-agent-warden

## Description

Local MCP audit proxy — audit logs, policy enforcement, secret scrubbing and kill switch between Claude Code and any MCP server

## Trust

- **Trust score (0–1):** 0.29
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/yli769227-jpg/agent-warden)

## 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": "yli769227-jpg-agent-warden"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/yli769227-jpg-agent-warden` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/yli769227-jpg-agent-warden/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