What it does
aidocs provides OpenAI documentation as MCP tools that query the public OpenAI docs sites. Its eight core tools search and fetch documentation pages, list docs and guides, return a document outline, search and fetch changelog entries, and retrieve the API reference.
It suits situations where a client needs OpenAI documentation, changelog details or API reference content through MCP. aidocs is a clean-room rebuild of the core surface of the OpenAI docs MCP server, with new code. No credentials are needed, because the documentation sites are public.
Each tool name is a CLI subcommand that takes one JSON object as its argument. The docs base URL can optionally be changed with the OPENAI_DOCS_BASE_URL setting; the default is the OpenAI platform docs. The project is released under the MIT licence.
Limitations and requirements
Only the eight core tools are included. Model listing and metadata, assistants and threads, audio and realtime docs, cookbook content beyond guides, community tools, and billing and usage docs are not covered. Fetch failures return the underlying network or upstream error.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.CloudCorpRecords/aidocs
OpenAI docs, guides, changelog and API reference as MCP tools.
v0.1.0As shown on registry.modelcontextprotocol.io when we last read it