# ask-a-friend-mcp

> ask-a-friend-mcp — mbettan-ask-a-friend-mcp. Use this tool when you need to validate AI responses with a second opinion from a different model, or to peer-review AI work while maintaining data privacy. It solves the problem of ensuring AI accuracy and reliability by allowing models like Claude, ChatGPT, and Gemini to cross-check their outputs with alternative models like Claude Opus 5.5 or Gemini 3.8 Flash. It takes AI responses as input, scrubs personally identifiable information (PII), and outputs validated responses after peer-review with a different frontier model.

Canonical page: https://skillsregistry.net/skills/mbettan-ask-a-friend-mcp  
JSON: https://api.skillsregistry.net/v1/skills/mbettan-ask-a-friend-mcp

## Description

Even your AI needs a second opinion. A self-hosted MCP server on Google Cloud Run that lets Claude, ChatGPT, Cursor, and Gemini CLI peer-review their work with a different frontier model — Claude Opus 5.5 or Gemini 3.8 Flash on Vertex AI — with PII scrubbed before anything leaves your server.

## Trust

- **Trust score (0–1):** 0.88
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/mbettan/ask-a-friend-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": "mbettan-ask-a-friend-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mbettan-ask-a-friend-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mbettan-ask-a-friend-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