OpenAI文档MCP服务器 - 权威开发者文档搜索与GPT-5.4升级指南

openai-docs by openai/skills

747 周安装量

15,700 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/openai/skills --skill openai-docs

AI/机器学习开发 API

🇨🇳中文介绍

OpenAI 文档

使用 developers.openai.com 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。此技能也可能从 references/ 目录加载特定文件，用于模型选择和 GPT-5.4 特定请求，但当前 OpenAI 文档始终具有权威性。仅当 MCP 服务器已安装但未返回有意义结果时，才应回退到网络搜索。

快速开始

使用 mcp__openaiDeveloperDocs__search_openai_docs 查找最相关的文档页面。
使用 mcp__openaiDeveloperDocs__fetch_openai_doc 提取确切的章节并准确引用/转述。
仅当您需要浏览或发现页面而没有明确查询时，才使用 mcp__openaiDeveloperDocs__list_openai_docs。
当问题涉及模型选择或 GPT-5.4 升级时，仅从 references/ 加载相关文件。

OpenAI 产品概览

Apps SDK：通过提供 Web 组件 UI 和一个向 ChatGPT 暴露您应用工具的 MCP 服务器，来构建 ChatGPT 应用。
Responses API：一个为智能体工作流中有状态、多模态、使用工具的交互而设计的统一端点。
Chat Completions API：根据包含对话的消息列表生成模型响应。
Codex：OpenAI 用于软件开发的编码智能体，可以编写、理解、审查和调试代码。
gpt-oss：根据 Apache 2.0 许可证发布的开源权重 OpenAI 推理模型（gpt-oss-120b 和 gpt-oss-20b）。

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

如果缺少 MCP 服务器

如果 MCP 工具失败或没有可用的 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/沙盒限制而失败，立即使用提升的权限重试同一命令，并附上一句理由说明以请求批准。暂时不要要求用户运行它。
仅当提升权限的尝试也失败时，再要求用户运行安装命令。
要求用户重启 Codex。
重启后重新运行文档搜索/获取。

明确产品范围和请求类型：是一般文档查找、模型选择、GPT-5.4 升级还是 GPT-5.4 提示词升级。
如果是模型选择请求，加载 references/latest-model.md。
如果是明确的 GPT-5.4 升级请求，加载 references/upgrading-to-gpt-5p4.md。
如果升级可能需要更改提示词，或者工作流程是研究密集型、工具密集型、面向编码、多智能体或长时间运行的，则同时加载 references/gpt-5p4-prompting-guide.md。
使用精确查询搜索文档。
获取最佳页面和所需的确切章节（尽可能使用 anchor）。
对于 GPT-5.4 升级审查，始终明确每个使用场景的输出：目标模型、起始推理建议、相关的 phase 评估、提示词块和兼容性状态。
用简洁的指导进行回答并引用文档来源，仅将参考文件用作辅助上下文。

references/latest-model.md -> 用于模型选择和“最佳/最新/当前模型”问题；在回答前，根据当前 OpenAI 文档验证每项建议。
references/upgrading-to-gpt-5p4.md -> 仅用于明确的 GPT-5.4 升级和升级规划请求；在回答前，根据当前 OpenAI 文档验证检查清单和兼容性指导。
references/gpt-5p4-prompting-guide.md -> 用于 GPT-5.4 的提示词重写和提示词行为升级；在回答前，根据当前 OpenAI 文档验证提示词指导。

将 OpenAI 文档视为事实来源；避免猜测。
保持引用简短并在政策限制内；优先使用带引用的转述。
如果多个页面存在差异，请指出差异并同时引用两者。
参考文件仅为便利指南；对于易变的指导，例如推荐模型、升级说明或提示词建议，始终以当前 OpenAI 文档为准。
如果文档未涵盖用户需求，请说明并提供后续步骤。

对于 OpenAI 相关问题，始终先使用 MCP 文档工具，再进行任何网络搜索。
如果 MCP 服务器已安装但未返回有意义的结果，则使用网络搜索作为备用方案。
当回退到网络搜索时，限制在官方 OpenAI 域名（developers.openai.com, platform.openai.com）并引用来源。

🇺🇸English

OpenAI Docs

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. This skill may also load targeted files from references/ for model-selection and GPT-5.4-specific requests, but current OpenAI docs remain authoritative. Only if the MCP server is installed and returns no meaningful results should you fall back to web search.

Quick start

Use mcp__openaiDeveloperDocs__search_openai_docs to find the most relevant doc pages.
Use mcp__openaiDeveloperDocs__fetch_openai_doc to pull exact sections and quote/paraphrase accurately.
Use mcp__openaiDeveloperDocs__list_openai_docs only when you need to browse or discover pages without a clear query.
Load only the relevant file from references/ when the question is about model selection or a GPT-5.4 upgrade.

OpenAI product snapshots

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.

If MCP server is missing

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.

Workflow

Clarify the product scope and whether the request is general docs lookup, model selection, a GPT-5.4 upgrade, or a GPT-5.4 prompt upgrade.
If it is a model-selection request, load references/latest-model.md.
If it is an explicit GPT-5.4 upgrade request, load references/upgrading-to-gpt-5p4.md.
If the upgrade may require prompt changes, or the workflow is research-heavy, tool-heavy, coding-oriented, multi-agent, or long-running, also load references/gpt-5p4-prompting-guide.md.
Search docs with a precise query.
Fetch the best page and the exact section needed (use anchor when possible).
For GPT-5.4 upgrade reviews, always make the per-usage-site output explicit: target model, starting reasoning recommendation, phase assessment when relevant, prompt blocks, and compatibility status.
Answer with concise guidance and cite the doc source, using the reference files only as helper context.

Reference map

Read only what you need:

references/latest-model.md -> model-selection and "best/latest/current model" questions; verify every recommendation against current OpenAI docs before answering.
references/upgrading-to-gpt-5p4.md -> only for explicit GPT-5.4 upgrade and upgrade-planning requests; verify the checklist and compatibility guidance against current OpenAI docs before answering.
references/gpt-5p4-prompting-guide.md -> prompt rewrites and prompt-behavior upgrades for GPT-5.4; verify prompting guidance against current OpenAI docs before answering.

Quality rules

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.
Reference files are convenience guides only; for volatile guidance such as recommended models, upgrade instructions, or prompting advice, current OpenAI docs always win.
If docs do not cover the user’s need, say so and offer next steps.

Tooling notes

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.

Weekly Installs

622

Repository

openai/skills

GitHub Stars

15.3K

First Seen

Feb 1, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykFail

Installed on

codex571

opencode536

gemini-cli524

github-copilot510

kimi-cli499

amp497

agent-browser 浏览器自动化工具 - Vercel Labs 命令行网页操作与测试

140,500 周安装