Chatgpt MCP Connect
Connect custom MCP servers or an MCP runtime to ChatGPT. Use when the user asks whether an MCP can be used by ChatGPT, or asks to expose, deploy, authenticate, configure, aggregate, or connect MCP capabilities for ChatGPT. Covers direct leaf servers, MCPX runtime aggregation, hosted and local Streamable HTTP, stdio bridging, OAuth 2.1, Cloudflare Workers/Tunnel, Tailscale Funnel, and real verification inside ChatGPT.
Install
npx skills add yoruuuchan/chatgpt-mcp-connect --skill chatgpt-mcp-connectgit clone --depth 1 https://github.com/yoruuuchan/chatgpt-mcp-connect.git /tmp/chatgpt-mcp-connect
mkdir -p ~/.claude/skills
cp -r /tmp/chatgpt-mcp-connect/. ~/.claude/skills/chatgpt-mcp-connectPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# chatgpt-mcp-connect Use this skill when the target client is **ChatGPT**. ## Start from here, not from first principles ChatGPT can use custom remote MCP servers. Do not spend the task rediscovering that, and do not re-research the basic architecture. The public MCP boundary needs four things at once: ```text public HTTPS URL + Streamable HTTP + OAuth 2.1 (DCR/compatible client registration + PKCE) + a tool count it accepts ``` Everything you do is to satisfy those four. Read [`docs/architecture.md`](./docs/architecture.md) in this repo for the full map. ## Decide the public boundary before you build First ask: **is the user exposing one leaf MCP, or do they actually want one persistent connection to several Workspaces, Skills, or MCP servers?** | Goal | Do this | |---|---| | One application-specific MCP | Follow the direct leaf-server decision table below | | Several local MCPs / Skills / Workspaces behind one connector | Start from [`recipes/mcpx`](./recipes/mcpx/) and use MCPX as the runtime boundary | Do not automatically build one public OAuth + tunnel + ChatGPT connector per stdio server when the user's real goal is aggregation. MCPX can keep stdio upstream MCPs private behind the runtime and expose them through its stable `mcp_tool` interface. For a **direct leaf server**, answer two questions and follow the matching recipe in [`recipes/`](./recipes/): | Speaks HTTP? | Has OAuth? | Do this | |---|---|---|
Details
- Skill name
chatgpt-mcp-connect- Repository
- yoruuuchan/chatgpt-mcp-connect
- License
- MIT
- Repo updated
- 27 October 2026
FAQ
What does the Chatgpt MCP Connect skill do?
Connect custom MCP servers or an MCP runtime to ChatGPT. Use when the user asks whether an MCP can be used by ChatGPT, or asks to expose, deploy, authenticate, configure, aggregate, or connect MCP capabilities for ChatGPT. Covers direct leaf servers, MCPX runtime aggregation, hosted and local Streamable HTTP, stdio bridging, OAuth 2.1, Cloudflare Workers/Tunnel, Tailscale Funnel, and real verification inside ChatGPT.
How do I install the Chatgpt MCP Connect skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add yoruuuchan/chatgpt-mcp-connect --skill chatgpt-mcp-connect. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Chatgpt MCP Connect popular?
It lives in yoruuuchan/chatgpt-mcp-connect, which has 5 GitHub stars and 0 forks.
Related skills
Comprehensive Engineering Cybernetics
5sjysjysjy728/comprehensive-engineering-cybernetics-skill
把合同或需求驱动的项目交付,以及 AI 科研的 idea、实现和实验,转化为可测量、可纠偏、资源受限且不静默降级的反馈闭环。用于需要逐项达到验收指标、把能力有限的现有资源组织成更强系统、保持 claim-to-code 保真、在不确定性下迭代或控制算力/时间/成本的复杂任务;不自动用于一步即可完成的低风险小改动、纯历史介绍或单纯控制理论推导。
AI Video Sannong
5Frank-oll/ai-video-creator
端到端制作竖屏 AI 妙招短视频(默认 3 镜 × 5 秒 = 15 秒,9:16)。题材通用:三农园艺、阳台种菜、美食、家居清洁收纳、宠物、育儿等都行,开场先问用户选题方向,不预设。工作流:方向确认 → 热门检索/对标视频拆解 → 双锚定(视觉一致 + 叙事承接)→ 全中文分镜 prompt → 一致性生图(火山 Seedream)→ 图生视频 + 原生 AI 配音(火山 Seedance 1.5 pro)→ ffmpeg 自动拼接成片。单网关单 key(火山 ARK,ark- 开头)。支持标准/快速/托管三档确认模式,生成物 agent 先做多模态自检再交付。当用户说"做 AI 视频""做一条妙招短视频""三农/阳台种菜/园艺短视频""美食/清洁/收纳妙招视频""复刻这种短视频""按这个对标拍一条",或上传带"内容由 AI 生成"标识的妙招类短视频做对标时,触发这个 skill。不要跟 script-washing(洗稿)、prompt-polish(单条提示词打磨)混用——这个是从选题到成片的端到端视频生产。
Dingtalk Bridge
5mguozhen/dingtalk-bridge
DingTalk group chat bridge for Claude Code. Send markdown/text messages to DingTalk groups, receive @mentions and auto-execute via Claude CLI, run a 24/7 Stream bot. Triggers: dingtalk, send dingtalk, dingtalk bot, dingtalk message, send group message, 钉钉, 发群消息, 钉钉机器人
AI Slop Detector
5MahmoudHalat/slop-cop
Universal prose audit. Scores writing on TWO axes — AI-Slop (does this read like AI wrote it?) and Comprehension (can a fresh reader follow this?). Use PROACTIVELY as a mandatory final QA pass on ANY prose generated for humans to read — every email (internal or external), proposal, report, status update, blog post, social post, doc, or chat message — before delivering it, even when nobody asked for an audit. Also use whenever the user wants to audit, critique, score, rewrite, or humanize prose: "audit this", "review this", "is this AI", "does this sound like AI", "humanize this", "make this le
Dspy Rb
5vicentereig/dspy-rb-skill
Build type-safe LLM applications with DSPy.rb - Ruby's programmatic prompt framework with signatures, modules, agents, and optimization
AI Resume Generator
5haorenhao58-sketch/ai-resume-generator
一键生成互联网AI方向简历的通用工具。当用户提到'生成简历''写简历''AI简历''求职简历''更新简历',或提到想投递AI产品经理、AI运营、AI工程师、AI商业化、Prompt Engineer、LLM应用、AIGC等AI相关岗位时触发。也适用于用户说'帮我整理项目经历''优化简历表述''简历润色'等场景。该skill通过深度引导候选人输入个人信息与项目细节,运用'问题→方案→量化结果'三段式写作范式,生成突出AI思维与产品化能力的高质量简历,支持Markdown和Word两种输出格式。
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.