> For the complete documentation index, see [llms.txt](https://docs.kick.co/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.kick.co/ai/mcp.md).

# MCP

- [Quickstart](https://docs.kick.co/ai/mcp/mcp-quickstart.md): Your AI can read and update your Kick data through conversation, and connect to all your other tools in the same place.
- [Connectors](https://docs.kick.co/ai/mcp/connectors.md): Use your preferred AI tool to query transactions, analyze financials, and automate workflows; Kick works with any MCP-compatible assistant.
- [Connect Claude](https://docs.kick.co/ai/mcp/connectors/connect-claude.md): Add Kick from Claude's connector directory for deep context on your clients' financials. Query transactions, generate reports, create rules, and execute bookkeeping changes in one conversation
- [Connect ChatGPT](https://docs.kick.co/ai/mcp/connectors/connect-chatgpt.md): Ask ChatGPT to analyze your clients' books and take action. Pull reports, categorize transactions, and automate rules without leaving the conversation
- [Connect Gemini](https://docs.kick.co/ai/mcp/connectors/connect-gemini.md): Connect Gemini to Kick and combine visual and conversational AI. Upload receipts, query transactions, analyze trends, and update bookkeeping, all in one multimodal conversation.
- [Connect Perplexity](https://docs.kick.co/ai/mcp/connectors/connect-perplexity.md): Ask Perplexity questions about client data and give it commands. Query transactions, generate reports, create automation rules, all with cited, verified responses
- [Connect Microsoft Copilot](https://docs.kick.co/ai/mcp/connectors/connect-microsoft-copilot.md): Build custom AI agents that can read your clients' Kick data, generate reports, and execute approved bookkeeping changes, all through natural conversation in your organization's Copilot
- [Connect Cursor](https://docs.kick.co/ai/mcp/connectors/connect-cursor.md): Give Cursor full control of your clients' books. Read transactions, generate reports, create rules, and execute bookkeeping changes without leaving your editor
- [Connect custom AI tools](https://docs.kick.co/ai/mcp/connectors/connect-custom-ai-tools.md): Your AI tool supports MCP but we don't have a guide for it yet? Use these connection details to give it full access to read and update your Kick data
- [Use Case Library](https://docs.kick.co/ai/mcp/mcp-use-case-library.md): Explore examples of MCP workflows you can run with Kick
- [MCP Example Workflows](https://docs.kick.co/ai/mcp/mcp-use-case-library/mcp-example-workflows.md): Sample AI assistant prompts for daily operations, period close, investigation, cleanup, deliverables, onboarding, and reusable MCP routines.
- [Kick Tool List](https://docs.kick.co/ai/mcp/available-tools.md): Every tool Kick MCP gives your AI assistant, grouped by area, with what each one reads or changes, its operations, and the plan it needs.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.kick.co/ai/mcp.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.