> For the complete documentation index, see [llms.txt](https://docs.bunny.com/guide/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.bunny.com/guide/tour/bunny-ai.md). # Bunny AI Bunny is built to be driven by AI as much as by people. Whether you want to ask questions about your revenue in plain language, connect your own AI assistant to your billing data, or have your AI coding assistant integrate Bunny for you, there's a purpose-built way in. There are three ways to put AI to work with Bunny, depending on what you're trying to do: ### RevOps Agent **Best for:** day-to-day questions and tasks, no setup required. The RevOps Agent is Bunny's built-in AI assistant. Ask it about your accounts, subscriptions, and metrics — or have it carry out tasks like creating subscriptions, applying discounts, and exporting customer lists — in plain language. It's available right inside Bunny via the chat window, and in Slack as a bot you can message. If you just want answers and actions without wiring anything up, start here. [Read more about the RevOps Agent →](/guide/tour/bunny-ai/revops-agent.md) ### MCP Server **Best for:** connecting your own AI assistant to your live Bunny data. The Bunny MCP server lets you connect external AI clients — such as Claude and ChatGPT — directly to your billing platform using the open [Model Context Protocol](https://modelcontextprotocol.io/). Once connected over OAuth, your assistant gains **31 tools** and a set of pre-computed context resources: it can read accounts, subscriptions, and revenue data, and drive quoting, subscription management, and record updates, all within your existing permission scope. Every tool runs as the authenticated user, read-only tools cannot change data, and quotes are always drafts until explicitly applied. This is the same toolset that powers the RevOps Agent, made available to the client of your choice. [Read more about the MCP Server →](/guide/tour/bunny-ai/mcp-server.md) ### AI Agent Skills **Best for:** developers integrating Bunny, and anyone who wants their own assistant to use Bunny well. Bunny publishes an open-source [Agent Plugin](https://agent-plugins.org/) — an open standard for packaging skills and MCP servers together — that installs into Claude Code, VS Code, Cursor, Gemini CLI, OpenAI Codex, and other compatible tools. It carries fourteen skills in two families: * **Integration skills** teach your assistant to work with Bunny's GraphQL API, SDKs, React components, webhooks, and customer portal — so it builds billing features using correct, current patterns instead of guesswork. * **Operator skills** teach it to use the MCP tools well: which tool answers which question, how to read revenue metrics correctly, and why a subscription change goes through a quote. [Read more about Skills →](/guide/tour/bunny-ai/skills-bunny-ai-toolkit.md) ### Which one do I need? | If you want to… | Use | | ------------------------------------------------------------------ | ------------------------------------------------------------------ | | Ask questions and run tasks inside Bunny or Slack, with no setup | [RevOps Agent](/guide/tour/bunny-ai/revops-agent.md) | | Connect Claude, ChatGPT, or another AI client to your Bunny data | [MCP Server](/guide/tour/bunny-ai/mcp-server.md) | | Integrate Bunny into your own app with an AI coding assistant | [AI Agent Skills](/guide/tour/bunny-ai/skills-bunny-ai-toolkit.md) | | Get better, more consistent results from a client you've connected | [AI Agent Skills](/guide/tour/bunny-ai/skills-bunny-ai-toolkit.md) | ### How they fit together The three are layers on one foundation, not alternatives: * The **MCP server** provides the capability — the tools and data an assistant can reach. * The **skills** provide the strategy — which tool to reach for, in what order, and how to interpret the result. * The **RevOps Agent** is both, pre-assembled and ready to use. That distinction matters when you connect your own client. A general-purpose assistant pointed at the MCP server has the same capabilities as the RevOps Agent but none of its guidance, so its tool choices and phrasing will differ. Installing the plugin's operator skills is what closes that gap. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.bunny.com/guide/tour/bunny-ai.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.