# crusty-proxy

> crusty-proxy — stefanhoth-crusty-proxy. Use this tool when you need to securely manage API access for AI agents and control their capabilities. The crusty-proxy solves the problem of exposing sensitive API keys and restricts agent tools to read-only or delete access. It takes in API requests as input and outputs controlled API responses, ideal for use cases where API key security and agent permission management are crucial.

Canonical page: https://skillsregistry.net/skills/stefanhoth-crusty-proxy  
JSON: https://api.skillsregistry.net/v1/skills/stefanhoth-crusty-proxy

## Description

MCP proxy that keeps API keys away from your AI agents and lets you cherry-pick their tools - read ✅, delete ⛔. Built for OpenClaw, works with any MCP client.

## Trust

- **Trust score (0–1):** 0.78
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/stefanhoth/crusty-proxy)

## 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": "stefanhoth-crusty-proxy"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/stefanhoth-crusty-proxy` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/stefanhoth-crusty-proxy/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