codex-chatgpt-bridge — security grade SAFE, quality 72/100

Security audit verdict: SAFE · quality 72/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by Zhenyu98 · MCP Server · ★ 168

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is codex-chatgpt-bridge safe to install? View the security audit →

About codex-chatgpt-bridge

Codex ChatGPT Bridge A safe bridge that lets Codex and ChatGPT hand off coding work — ChatGPT does the heavy thinking, Codex keeps local execution and verification under control. Save Codex tokens · ChatGPT plans, Codex executes · Local execution stays scoped and re-keyable Why · Quick Start · Agent Setup · Routing · Security · FAQ · 简体中文 Why Long Codex sessions burn quota on planning, re-reading, and repe

agentic-workflowai-agentschatgptcodex-skillmcp-servermulti-agenttoken-saving

Quick Facts

Stars168
Forks20
LanguagePowerShell
CategoryMCP Server
LicenseMIT
Quality Score71.8206974207368/100
Open Issues2
Last Updated2026-07-30
Created2026-06-22
Platformscodex, mcp
Est. Tokens~13k

Compatible Skills

These tools work well together with codex-chatgpt-bridge for enhanced workflows:

  • codex_auto_register — semantic(0.28)+complementary+similar_pop+shared_platform (50%)
  • gpt-team-register — semantic(0.27)+complementary+similar_pop+shared_platform (49%)
  • openai-oauth — semantic(0.26)+complementary+similar_pop+shared_platform (49%)
  • qoreon — semantic(0.25)+complementary+similar_pop+shared_platform (49%)
  • codex-profiles — semantic(0.24)+complementary+similar_pop+shared_platform (48%)

codex-chatgpt-bridge alternative? Top 6 similar tools

Looking for a codex-chatgpt-bridge alternative? If you're comparing codex-chatgpt-bridge 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.

  • vibe-check-mcp-server by PV-Bhat · ⭐ 502

    Vibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineeri

  • AgenticGoKit by AgenticGoKit · ⭐ 169

    Open-source Agentic AI framework in Go for building, orchestrating, and deploying intelligent agents. LLM-agno

  • captain-claw by kstevica · ⭐ 163

    Self-hosted framework for orchestrating fleets of specialist AI agents — ensemble reasoning and a full agentic

  • golf by golf-mcp · ⭐ 840

    Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth,

  • Wax by christopherkarani · ⭐ 797

    Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple S

  • wcgw by rusiaaman · ⭐ 674

    Shell and coding agent on mcp clients

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular PowerShell Agent Tools

Frequently Asked Questions

What is codex-chatgpt-bridge?

codex-chatgpt-bridge is A safe bridge for Codex and ChatGPT to hand off coding work, save tokens, and keep local execution under control.. It is categorized as a MCP Server with 168 GitHub stars.

What programming language is codex-chatgpt-bridge written in?

codex-chatgpt-bridge is primarily written in PowerShell. It covers topics such as agentic-workflow, ai-agents, chatgpt.

How do I install or use codex-chatgpt-bridge?

You can find installation instructions and usage details in the codex-chatgpt-bridge GitHub repository at github.com/Zhenyu98/codex-chatgpt-bridge. The project has 168 stars and 20 forks, indicating an active community.

What license does codex-chatgpt-bridge use?

codex-chatgpt-bridge is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to codex-chatgpt-bridge?

The top alternatives to codex-chatgpt-bridge on Agent Skills Hub include vibe-check-mcp-server, AgenticGoKit, captain-claw. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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:

View on GitHub → Browse MCP Server tools