# ai-runtime-guard

> ai-runtime-guard — runtimeguard-ai-runtime-guard. Use this tool when you need to enforce security policies and boundaries for AI agents, preventing unauthorized file or shell actions without requiring retraining or workflow changes. It sits between the AI agent and system, allowing for configuration and control of agent actions. Ideal for use cases where security and compliance are critical, such as protecting sensitive data or preventing malicious activity.

Canonical page: https://skillsregistry.net/skills/runtimeguard-ai-runtime-guard  
JSON: https://api.skillsregistry.net/v1/skills/runtimeguard-ai-runtime-guard

## Description

ai-runtime-guard is an MCP server that sits between your AI agent and your system, enforcing a policy layer before any file or shell action takes effect. No retraining, no prompt engineering, no changes to your agent or workflow, just install, configure once, and your agent operates within the boundaries you set.

## Trust

- **Trust score (0–1):** 0.18
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/xhlzv9sed3)
- **Repository:** <https://github.com/runtimeguard/runtime-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": "runtimeguard-ai-runtime-guard"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/runtimeguard-ai-runtime-guard` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/runtimeguard-ai-runtime-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