by openai · MCP Server · ★ 616
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 616 |
| Forks | 135 |
| Language | Go |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 64/100 |
| Open Issues | 12 |
| Last Updated | 2026-11-05 |
| Created | 2025-12-10 |
| Platforms | cli, codex, go, mcp |
| Est. Tokens | ~19k |
Secure MCP Tunnel client is the customer-run agent behind Secure MCP Tunnel. It connects a private or localhost MCP (Model Context Protocol) server to ChatGPT, Codex, the Responses API, and AgentKit through an OpenAI-hosted MCP tunnel endpoint, while keeping the MCP server off the public internet.
These tools work well together with tunnel-client for enhanced workflows:
Looking for a tunnel-client alternative? If you're comparing tunnel-client with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
MCP Aggregator, Orchestrator, Middleware, Gateway in one docker
An MCP client for Neovim that seamlessly integrates MCP servers into your editing workflow with an intuitive i
A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing
MCP Server Framework and Tool Development library for building custom capabilities into agents.
ChatGPT CLI is a powerful, multi-provider command-line interface for working with modern LLMs. It supports Ope
Lightweight Agent Workstation for Codex + Claude code + keke-agent — with dots, task scheduler, git worktree &
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: