# Agent Guardrail MCP

> Use this tool when you need to protect AI agent interactions from malicious prompt injections and sensitive information exposure. It solves problems related to security and compliance by detecting and preventing potential threats, while also providing an audit trail for transparency. The Agent Guardrail MCP takes in AI agent inputs and outputs, and returns redacted and secured responses.

Canonical page: https://skillsregistry.net/skills/ss-2303-agent-guardrail-mcp  
JSON: https://api.skillsregistry.net/v1/skills/ss-2303-agent-guardrail-mcp

## Description

Provides prompt injection detection, PII/secrets redaction, and an audit trail for AI agents via MCP tools.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/dmqmxgj5rp)
- **Repository:** <https://github.com/ss-2303/injection-pii-guardrail-mcp>

## 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": "ss-2303-agent-guardrail-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ss-2303-agent-guardrail-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ss-2303-agent-guardrail-mcp/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