openai-mcp
MCP server that bridges ChatGPT Plus/Pro to Claude Code, enabling chat, deep research, and image generation via your own account.
README
openai-mcp
Use your ChatGPT Plus or Pro subscription inside Claude Code, Codex, and any MCP client.
What it does
openai-mcp exposes 15 MCP tools that forward requests directly to ChatGPT's backend API. No proxy process. No separate account. Your token, your quota.
Works with Claude Code, Codex CLI, and any client that speaks the MCP protocol over stdio.
Install
pip install openai-mcp
Or with pipx for an isolated install:
pipx install openai-mcp
Setup
openai-mcp setup
The wizard will:
- Look for an existing Codex auth token at
~/.codex/auth.json - If not found, prompt you to paste a ChatGPT session token
- Save credentials to
~/.openai-mcp/token.json
Configure in Claude Code
Add the following to ~/.claude.json (under mcpServers):
{
"mcpServers": {
"openai": {
"type": "stdio",
"command": "openai-mcp",
"args": ["run", "--stdio"]
}
}
}
Restart Claude Code after saving. Tools appear under the openai namespace.
Tools
| Tool | What it does |
|---|---|
chat |
Chat with GPT-5.x, Pro models, o3, o3-pro |
deep_research |
Web-augmented search answer (~30 s) |
deep_research_heavy |
Long-form Deep Research via gpt-5-5-pro (5–30 min, uses monthly quota) |
account_status |
ChatGPT plan and enabled features |
list_models |
All models available to your account |
memory_list |
List ChatGPT memories (PII redacted) |
memory_search |
Search ChatGPT memories by keyword |
custom_instructions_get |
Retrieve your ChatGPT custom instructions |
list_codex_envs |
List Codex environments |
list_codex_tasks |
List recent Codex tasks |
list_custom_gpts |
List your custom GPTs |
list_conversations |
Recent ChatGPT conversations |
list_tasks |
Scheduled ChatGPT tasks |
list_apps |
Connected apps and connectors |
Architecture
Native Python implementation — no proxy. The server calls
/backend-api/conversation (SSE) directly using curl_cffi for TLS
impersonation. Vendored POW and Turnstile solvers handle the OpenAI Sentinel
challenge. See NOTICES for attribution.
~/.codex/auth.json (or ~/.openai-mcp/token.json)
|
openai-mcp (stdio MCP server)
|
curl_cffi → chatgpt.com /backend-api/conversation (SSE)
|
14 read tools + 1 heavy DR tool
Limitations
- Deep Research quota: 248 requests/month on Pro; lower on Plus.
- image_gen: stub is present but not yet wired to a working endpoint.
- memory_add: read-only — the write endpoint returns 405; tool is not registered.
- Requires an active ChatGPT Plus or Pro subscription.
Development
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
pytest
License
MIT. See NOTICES for third-party attributions.
Acknowledgments
- lanqian528/chat2api — POW and Turnstile solver code (MIT)
- basketikun/chatgpt2api — survey of ChatGPT backend API patterns
- 7836246/cursor2api — survey of Cursor API patterns
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。