> For the complete documentation index, see [llms.txt](https://doc.commandersact.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doc.commandersact.com/features/mcp-server-closed-beta.md).

# Commanders Act MCP (closed beta)

## Explore your Commanders Act configuration with AI

Connect **ChatGPT or Claude** to Commanders Act and ask questions about your real configuration in plain language. Understand where data comes from, how tags and destinations are configured, and what monitoring information is available — without switching between multiple interfaces.

**Read-only by design:** The MCP lets your AI assistant retrieve and analyze available information. It cannot change or deploy your Commanders Act configuration.

## Start in three steps

1. [**Connect ChatGPT or Claude**](/features/mcp-server-closed-beta/getting-started-closed-beta.md) — Add the Commanders Act MCP endpoint to your AI assistant and sign in with your existing Commanders Act account.
2. **Ask your first question** — `List the Commanders Act sites available to my account.`
3. [**Explore real-world prompts**](/features/mcp-server-closed-beta/use-cases-and-prompt-library.md) — Trace event flows, compare websites, investigate tracking and review privacy data.

**To obtain the MCP server URL and access instructions, contact Commanders Act Support or your account manager.** Access is currently available to selected organizations during our controlled rollout. If your team has been invited but cannot connect, contact your Commanders Act account or support team.

## See what you can do

### Visualize a purchase event from collection to destinations

Ask the assistant to explain the expected flow of a purchase event through the parts of your Commanders Act configuration it can inspect. It can turn these relationships into an easy-to-read diagram and identify steps that still need verification.

![Example: purchase event configuration visualized in Claude using the Commanders Act MCP](https://1259070148-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-Mk6XpTQ2LaRLcr2tA-d%2Fuploads%2FDtlEDoGF9OYkPepi1BEx%2Fmcp-claude-purchase.webp?alt=media)

[Try the purchase-event prompt](/features/mcp-server-closed-beta/use-cases-and-prompt-library.md#visualize-the-journey-of-a-purchase-event)

### Other useful investigations

* **Investigate a conversion drop:** review relevant collection alerts, data quality and configuration history.
* **Compare multiple websites or markets:** see differences between web tags, server-side settings and marketing destinations.
* **Explore CDP audiences:** organize available segments into likely marketing use cases.
* **Review privacy data:** use cookie scanner results and consent statistics to prepare a prioritized investigation.

Each example includes a **ready-to-copy prompt**, and several show an actual example result: [Explore the prompt library](/features/mcp-server-closed-beta/use-cases-and-prompt-library.md).

## What does it cover?

The MCP provides read access to available information across **Tag Management, Server-side, Sources & Destinations, Data & Audiences, Privacy, Monitoring, Reporting and Administration**.

It works with the user permissions of your Commanders Act account and supports existing **SSO and two-factor authentication (2FA)**.

For the complete list of supported areas, important limitations, data-handling guidance and frequently asked questions, see [Capabilities, Security & FAQ](/features/mcp-server-closed-beta/capabilities-security-and-faq.md).

## What the MCP does — and does not — verify

The assistant can analyze accessible configuration and monitoring data, but a configured tag does not prove that an event was actually delivered. External advertising-platform results are not automatically available. Ask the assistant to distinguish **verified configuration, possible explanations and missing evidence**.

**Ready to try it?** [Get started](/features/mcp-server-closed-beta/getting-started-closed-beta.md) · [Browse prompts](/features/mcp-server-closed-beta/use-cases-and-prompt-library.md)


---

# 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://doc.commandersact.com/features/mcp-server-closed-beta.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.