mcpField
A
aidocs

aidocs

Local
github.com/CloudCorpRecordsDeveloper Tools0Updated 2w ago
Repository

About aidocs

aidocs exposes public OpenAI documentation through a keyless MCP server and CLI. It is for users looking up docs, guides, changelog entries, and API reference material, with a defined core subset of eight tools.

Key features

  1. 01Search and fetch OpenAI documentation
  2. 02List docs and retrieve document outlines
  3. 03Search and fetch changelog entries
  4. 04Retrieve API reference material
  5. 05List OpenAI guides

Use cases

  1. 01Find documentation about an OpenAI feature
  2. 02Read a documentation page or its outline
  3. 03Check OpenAI changelog updates
  4. 04Look up API reference details

MCP support

Its MCP server exposes eight tools for searching and fetching OpenAI docs and changelog entries, listing docs and guides, retrieving outlines, and accessing API reference material. No credentials are required.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "cloudcorprecords-aidocs": {
      "command": "npx",
      "args": [
        "-y",
        "@reneturcios/aidocs"
      ]
    }
  }
}
Run commandnpx -y @reneturcios/aidocs

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@reneturcios/aidocs0.1.0
ocighcr.io/cloudcorprecords/aidocs:0.1.0

Tools

8

Saved tool list · updated 1w ago

ParameterTypeRequiredDescription
limitnumberNoMaximum number of search results to return (default 10).
querystringYesSearch terms to match against the OpenAI documentation.

Details

From the project README

aidocs

OpenAI documentation as MCP tools, talking to the public OpenAI docs sites. aidocs is a clean-room rebuild of the core surface of the OpenAI docs MCP server, under a new name: fresh code, no copied branding. It is keyless by design — the documentation sites are public, so no API key is required or demanded.

Tools (core subset, 8)

search_openai_docs, fetch_openai_doc, list_openai_docs, get_openai_doc_outline, search_openai_changelog, fetch_openai_changelog, get_api_reference, list_openai_guides.

Not in this subset: model listing and metadata tools, assistants and threads tools, audio and realtime docs tools, cookbook browsing beyond guides, community tools, and billing/usage docs tools.

Setup

No credentials. Optionally override the docs base with OPENAI_DOCS_BASE_URL (default https://platform.openai.com/docs). Fetch failures surface the underlying network or upstream error.

CLI

npx @reneturcios/aidocs search_openai_docs '{"query":"function calling"}'
npx @reneturcios/aidocs mcp        # stdio MCP server

Each tool name is a subcommand taking one JSON object argument.

MCP client config

{
  "mcpServers": {
    "aidocs": {
      "command": "npx",
      "args": ["-y", "@reneturcios/aidocs", "mcp"]
    }
  }
}

Docker

docker run -i ghcr.io/cloudcorprecords/aidocs

Development

npm install
npm run build
npm test

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.