# AgentGuard

> AgentGuard — princeixr-agentguard. Use this tool when you need to secure Google ADK agents from risky actions and ensure enterprise auditability. AgentGuard blocks malicious MCP actions, routes sensitive calls for approval, and provides a transparent audit trail. Ideal for organizations requiring enhanced security and compliance measures for their ADK agents, AgentGuard integrates with git for seamless implementation.

Canonical page: https://skillsregistry.net/skills/princeixr-agentguard  
JSON: https://api.skillsregistry.net/v1/skills/princeixr-agentguard

## Description

AgentGuard is the open-source security layer for Google ADK agents, blocking risky MCP actions, routing sensitive calls for approval, and delivering enterprise auditability.

## Trust

- **Trust score (0–1):** 0.80
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/princeixr/AgentGuard)

## 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": "princeixr-agentguard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/princeixr-agentguard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/princeixr-agentguard/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