openai-docs
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseOpenAI Docs
OpenAI文档
Provide authoritative, current guidance from OpenAI developer docs using the developers.openai.com MCP server. Always prioritize the developer docs MCP tools over web.run for OpenAI-related questions. Only if the MCP server is installed and returns no meaningful results should you fall back to web search.
使用developers.openai.com的MCP服务器,提供来自OpenAI开发者文档的权威、最新指导。对于OpenAI相关问题,始终优先使用开发者文档MCP工具,而非web.run。只有当MCP服务器已安装但未返回有意义结果时,才应退而使用网页搜索。
Quick start
快速开始
- Use to find the most relevant doc pages.
mcp__openaiDeveloperDocs__search_openai_docs - Use to pull exact sections and quote/paraphrase accurately.
mcp__openaiDeveloperDocs__fetch_openai_doc - Use only when you need to browse or discover pages without a clear query.
mcp__openaiDeveloperDocs__list_openai_docs
- 使用查找最相关的文档页面。
mcp__openaiDeveloperDocs__search_openai_docs - 使用提取准确的章节内容,并进行引用或改写。
mcp__openaiDeveloperDocs__fetch_openai_doc - 仅当你需要在没有明确查询词的情况下浏览或发现页面时,才使用。
mcp__openaiDeveloperDocs__list_openai_docs
OpenAI product snapshots
OpenAI产品概览
- Apps SDK: Build ChatGPT apps by providing a web component UI and an MCP server that exposes your app's tools to ChatGPT.
- Responses API: A unified endpoint designed for stateful, multimodal, tool-using interactions in agentic workflows.
- Chat Completions API: Generate a model response from a list of messages comprising a conversation.
- Codex: OpenAI's coding agent for software development that can write, understand, review, and debug code.
- gpt-oss: Open-weight OpenAI reasoning models (gpt-oss-120b and gpt-oss-20b) released under the Apache 2.0 license.
- Realtime API: Build low-latency, multimodal experiences including natural speech-to-speech conversations.
- Agents SDK: A toolkit for building agentic apps where a model can use tools and context, hand off to other agents, stream partial results, and keep a full trace.
- Apps SDK:通过提供Web组件UI和向ChatGPT暴露应用工具的MCP服务器,构建ChatGPT应用。
- Responses API:一个统一端点,专为智能体工作流中的有状态、多模态、工具调用交互而设计。
- Chat Completions API:从构成对话的消息列表中生成模型响应。
- Codex:OpenAI面向软件开发的编码智能体,可编写、理解、审查和调试代码。
- gpt-oss:OpenAI发布的开源权重推理模型(gpt-oss-120b和gpt-oss-20b),采用Apache 2.0许可证。
- Realtime API:构建低延迟、多模态体验,包括自然的语音对话。
- Agents SDK:用于构建智能体应用的工具包,模型可使用工具和上下文、移交至其他智能体、流式返回部分结果,并保留完整追踪记录。
If MCP server is missing
若MCP服务器缺失
If MCP tools fail or no OpenAI docs resources are available:
- Run the install command yourself:
codex mcp add openaiDeveloperDocs --url https://developers.openai.com/mcp - If it fails due to permissions/sandboxing, immediately retry the same command with escalated permissions and include a 1-sentence justification for approval. Do not ask the user to run it yet.
- Only if the escalated attempt fails, ask the user to run the install command.
- Ask the user to restart Codex.
- Re-run the doc search/fetch after restart.
如果MCP工具失效或无可用的OpenAI文档资源:
- 自行运行安装命令:
codex mcp add openaiDeveloperDocs --url https://developers.openai.com/mcp - 如果因权限/沙箱限制导致失败,立即使用提升的权限重试相同命令,并附上一句简短的审批理由。暂不要让用户运行该命令。
- 仅当提升权限的尝试也失败时,才请求用户运行安装命令。
- 请用户重启Codex。
- 重启后重新运行文档搜索/提取操作。
Workflow
工作流程
- Clarify the product scope (Codex, OpenAI API, or ChatGPT Apps SDK) and the task.
- Search docs with a precise query.
- Fetch the best page and the specific section needed (use when possible).
anchor - Answer with concise guidance and cite the doc source.
- Provide code snippets only when the docs support them.
- 明确产品范围(Codex、OpenAI API或ChatGPT Apps SDK)以及具体任务。
- 使用精准的查询词搜索文档。
- 获取最佳页面及所需的特定章节(尽可能使用)。
anchor - 以简洁的指导作答,并引用文档来源。
- 仅当文档支持时,才提供代码片段。
Quality rules
质量规则
- Treat OpenAI docs as the source of truth; avoid speculation.
- Keep quotes short and within policy limits; prefer paraphrase with citations.
- If multiple pages differ, call out the difference and cite both.
- If docs do not cover the user’s need, say so and offer next steps.
- 将OpenAI文档视为事实来源;避免猜测。
- 引用内容应简短且符合政策限制;优先采用改写并附带引用。
- 若多个页面内容存在差异,需指出差异并同时引用两个来源。
- 若文档未覆盖用户需求,需如实告知并提供后续步骤建议。
Tooling notes
工具说明
- Always use MCP doc tools before any web search for OpenAI-related questions.
- If the MCP server is installed but returns no meaningful results, then use web search as a fallback.
- When falling back to web search, restrict to official OpenAI domains (developers.openai.com, platform.openai.com) and cite sources.
- 对于OpenAI相关问题,始终优先使用MCP文档工具,再考虑网页搜索。
- 若MCP服务器已安装但未返回有意义结果,可退而使用网页搜索。
- 当使用后备网页搜索时,仅限官方OpenAI域名(developers.openai.com、platform.openai.com),并引用来源。