# Action Guard

> Use this tool when you need to enforce policy-based access control for AI assistant actions, restricting which tools can be invoked in MCP deployments. Action Guard provides fine-grained control, enabling deployments to define and enforce custom policies. It is ideal for use cases requiring secure and regulated AI tool usage, with a simple Python interface for policy definition and enforcement.

Canonical page: https://skillsregistry.net/skills/anon767-action-guard  
JSON: https://api.skillsregistry.net/v1/skills/anon767-action-guard

## Description

Action Guard is a Python MCP library for policy-based tool filtering. Enables MCP deployments to define and enforce policies that restrict which tools can be invoked, providing fine-grained access control for AI assistant actions. MIT-licensed.

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/anon767-action-guard)
- **Repository:** <https://github.com/anon767/mcp-action-guard>

## 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": "anon767-action-guard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/anon767-action-guard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/anon767-action-guard/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