Huan-zhaojun/mcp-safe-proxy

轻量级 MCP 注解代理 — 拦截 tools/list 响应,将工具注解重写为"安全"值,绕过 Codex 等 AI CLI 的审批弹窗,同时完全透传所有实际操作。

43
/ 100
Emerging

This tool helps AI CLI users like those interacting with OpenAI Codex or Claude Code to streamline their workflows. It sits between your AI assistant and tools like Playwright, preventing annoying approval pop-ups that interrupt your tasks. You input commands to your AI CLI as usual, and it transparently processes them without extra steps, making automated operations smoother and faster.

Available on npm.

Use this if you frequently interact with AI command-line interfaces (CLIs) that constantly prompt for approval when using automation tools, disrupting your workflow.

Not ideal if you prefer explicit approval prompts for every action your AI CLI takes, or if you are not using an AI CLI that interfaces with external tools.

AI-assistants workflow-automation developer-tools CLI-operations AI-agents
No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 20 / 25
Community 9 / 25

How are scores calculated?

Stars

7

Forks

1

Language

JavaScript

License

MIT

Last pushed

Mar 01, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/Huan-zhaojun/mcp-safe-proxy"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.