# AgentGuard

> Use this tool when you need to enforce AI policy compliance and ensure safety protocols are in place. AgentGuard provides a suite of 20 tools for preflight checks, risk scoring, and audit logging, accessible via HTTP at feedoracle.io. It helps solve problems related to AI risk management and regulatory compliance, accepting input requests and returning output logs and scores to inform policy enforcement decisions.

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

## Description

AgentGuard is a hosted MCP server from ToolOracle providing twenty AI safety tools for policy enforcement and compliance. It covers preflight checks, risk scoring, audit logging, and rate limiting, available via HTTP at feedoracle.io.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/agentguard)
- **Repository:** <https://github.com/tooloracle/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": "agentguard"
    }
  }
}
```

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