# guarded-infra-mcp

> guarded-infra-mcp — anurag444-guarded-infra-mcp. Use this tool when you need to provide secure, read-only access to Kubernetes and AWS resources for AI agents, with a deny-by-default policy and auditing capabilities. It solves the problem of controlling and monitoring AI agent access to sensitive infrastructure, while also evaluating their behavior and block rate. The tool accepts JSONL input and outputs an audit trail, making it ideal for use cases requiring strict access control and transparency.

Canonical page: https://skillsregistry.net/skills/anurag444-guarded-infra-mcp  
JSON: https://api.skillsregistry.net/v1/skills/anurag444-guarded-infra-mcp

## Description

Read-only Kubernetes and AWS access for AI agents, behind a deny-by-default policy gate with a JSONL audit trail and eval suites that score both per-call block rate and whole-trajectory behaviour.

## Trust

- **Trust score (0–1):** 0.93
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/anurag444/guarded-infra-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": "anurag444-guarded-infra-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/anurag444-guarded-infra-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/anurag444-guarded-infra-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