Model Context Protocol
The revenexx documentation is available as a Model Context Protocol (MCP) server. Point an MCP-capable assistant — Claude Code, Cursor, VS Code Copilot, and others — at it, and the assistant can search and read these docs while it works. Its answers and the code it generates stay grounded in the current revenexx Revenue Cloud documentation instead of a stale training snapshot.
Endpoint
The server is hosted, public, and needs no setup or credentials:
https://revenexx.dev/mcp
It speaks Streamable HTTP and serves the same documentation you're reading now. There's nothing to install and no API key to configure — add the URL to your client and start asking questions.
If you need to tell a customer what an AI agent can change in their tenant, What an AI agent can change covers which surfaces an agent can reach, which of them write, and the write access that comes from your own API key rather than from us.
Tools
Once connected, your assistant gains these tools:
Add it to your client
Setup is the same idea everywhere — add https://revenexx.dev/mcp as an HTTP server — but the exact steps and config format differ per tool.
Example prompts
Anything you'd look up in these docs, your assistant can now answer with the source in hand:
How do I authenticate against the revenexx API?Show me how to create an order with the CLI.What events does the webhooks service publish?Which SDKs are available and how do I install the web one?