# OpenAI Docs MCP server > Search and read OpenAI developer docs, the API reference and OpenAPI specs from your assistant. - Listing: https://mcp.tc/i/openai-docs - Connect: use the server's own URL `https://developers.openai.com/mcp` (no sign-in); clients connect to it directly. The listing link is a page, not an MCP endpoint. - Type: remote (Streamable HTTP) - Auth: none - Category: [Docs & Knowledge](https://mcp.tc/c/docs-knowledge) - Vendor: OpenAI - Verified: yes, mcp.tc checked that this is the official server (https://mcp.tc/verify). It says who runs the server, not that it is safe. - Homepage: ## About Connects your assistant to the OpenAI developer documentation on platform.openai.com, developers.openai.com and learn.chatgpt.com. It can search and browse doc pages, fetch a page or section as markdown, list API endpoints and return the OpenAPI spec for a given endpoint, with optional code samples by language. Runs as a hosted streamable HTTP endpoint at https://developers.openai.com/mcp. No sign-in or API key is needed. All five tools are read-only. ## What it can do - Search OpenAI docs across the platform, developers and learn sites - Browse and page through the crawled documentation list - Fetch a doc page as markdown, optionally a single section by anchor - List all OpenAI API endpoint URLs from the OpenAPI spec - Get the OpenAPI spec for one endpoint, filtered by code sample language ## Tools (5) - `search_openai_docs`: Search OpenAI docs across platform, developers and learn sites; returns URLs to fetch. (read-only) - `list_openai_docs`: List or browse crawled OpenAI doc pages with paging. (read-only) - `fetch_openai_doc`: Fetch a doc page as markdown, optionally limited to an anchor section. (read-only) - `list_api_endpoints`: List all OpenAI API endpoint URLs in the OpenAPI spec. (read-only) - `get_openapi_spec`: Return the OpenAPI spec for an endpoint URL, optionally filtered to code samples by language. (read-only) ## Example prompts - "Search the OpenAI docs for how to stream Responses API output" - "Fetch the OpenAI docs page on prompt caching and summarize the limits" - "Show the OpenAPI spec for the create response endpoint with Python examples" - "List the OpenAI API endpoints available in the spec" ## Install ### Claude Code 1. Run this in a terminal, in your project folder: ```bash claude mcp add --transport http openai-docs https://developers.openai.com/mcp ``` 2. Start Claude Code and type `/mcp`. **openai-docs** should show as connected. Add `--scope user` to make it available in every project, not just this one. ### Claude Desktop 1. Open **Settings → Connectors** and click **Add custom connector**. 2. Name it **OpenAI Docs** and paste this URL: ```url https://developers.openai.com/mcp ``` 3. Click **Add**. Its tools appear in the chat’s tools menu. Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too. ### claude.ai 1. Open the connector form on claude.ai. This button fills in the name and URL for you: [Add to claude.ai]() (opens connector settings) 2. Check that the URL reads `https://developers.openai.com/mcp` and click **Add**. 3. Turn it on in a chat from the tools menu. Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**. ### ChatGPT 1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**. 2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server. 3. Paste `https://developers.openai.com/mcp` as the server URL and choose **No authentication**. Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts. ### Cursor [Add to Cursor]() (opens Cursor) Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project): `mcp.json`: ```json { "mcpServers": { "openai-docs": { "url": "https://developers.openai.com/mcp" } } } ``` ### VS Code [Install in VS Code]() (opens VS Code) Or from a terminal: ```bash code --add-mcp '{"name":"openai-docs","type":"http","url":"https://developers.openai.com/mcp"}' ``` Or commit it to the repo in `.vscode/mcp.json`: `.vscode/mcp.json`: ```json { "servers": { "openai-docs": { "type": "http", "url": "https://developers.openai.com/mcp" } } } ``` ### Devin Desktop 1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows): `mcp_config.json`: ```json { "mcpServers": { "openai-docs": { "serverUrl": "https://developers.openai.com/mcp" } } } ``` 2. Refresh the MCP server list in Cascade. Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers. ### Codex ```bash codex mcp add openai-docs --url https://developers.openai.com/mcp ``` Or edit `~/.codex/config.toml` directly: `config.toml`: ```toml [mcp_servers.openai-docs] url = "https://developers.openai.com/mcp" ``` ### Gemini CLI ```bash gemini mcp add --transport http openai-docs https://developers.openai.com/mcp ``` This adds it to the current project. Add `-s user` to use it everywhere. ### Any client Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file. ```json { "mcpServers": { "openai-docs": { "type": "http", "url": "https://developers.openai.com/mcp" } } } ``` Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE. Client only starts local servers? Bridge it with `npx -y mcp-remote https://developers.openai.com/mcp`. ## Details - Server version: 1.0.0 - MCP protocol version: 2025-11-25 - Last checked: 2026-10-03 (reachable) - Listed: 2026-10-03 - Updated: 2026-10-04 --- Source: https://mcp.tc/i/openai-docs (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report