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

# MCP Servers

Choose the right Umbraco MCP server for your role and the Umbraco product you are working with.

Umbraco provides MCP servers for both the CMS and some of the add on products. Each one exposes a different set of tools through the [Model Context Protocol](/umbraco-in-ai/concepts/model-context-protocol.md), scoped to a specific role or Umbraco product.

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-cover data-type="image">Cover image</th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>CMS Developer MCP Server</strong></td><td>For Umbraco developers. Exposes the Umbraco Management API as MCP tools for content, schema, media, and workflow operations.</td><td></td><td><a href="/umbraco-in-ai/mcp/mcp-servers/cms-developer-mcp.md">CMS Developer MCP Server</a></td></tr><tr><td><strong>CMS Editor MCP Server</strong></td><td>For content editors and managers. Manage content, media, translations, and library elements through conversational AI.</td><td></td><td><a href="/umbraco-in-ai/mcp/mcp-servers/cms-editor-mcp.md">CMS Editor MCP Server</a></td></tr><tr><td><strong>Automate Developer MCP Server</strong></td><td>For developers using Umbraco Automate. Build, run, and monitor automations using AI. Beta.</td><td></td><td><a href="/umbraco-in-ai/mcp/mcp-servers/automate-developer-mcp.md">Automate Developer MCP Server</a></td></tr><tr><td><strong>Engage Developer MCP Server</strong></td><td>For developers using Umbraco Engage. Work with A/B tests, analytics, personas, segments, and campaigns using AI. Beta.</td><td></td><td><a href="/umbraco-in-ai/mcp/mcp-servers/engage-developer-mcp.md">Engage Developer MCP Server</a></td></tr><tr><td><strong>Forms Developer MCP Server</strong></td><td>For developers using Umbraco Forms. Build forms, manage submissions, and work with data sources using AI. Beta.</td><td></td><td><a href="/umbraco-in-ai/mcp/mcp-servers/forms-developer-mcp.md">Forms Developer MCP Server</a></td></tr></tbody></table>

## Choosing a Server

The right server depends on your role and which Umbraco product you are working with.

| Server                 | Intended for                      | Requires                                |
| ---------------------- | --------------------------------- | --------------------------------------- |
| CMS Developer MCP      | Umbraco developers                | Node.js 22+, API User                   |
| CMS Editor MCP         | Content editors and managers      | Hosted setup or Node.js 22+, API User   |
| Automate Developer MCP | Developers using Umbraco Automate | Umbraco Automate, Node.js 22+, API User |
| Engage Developer MCP   | Developers using Umbraco Engage   | Umbraco Engage, Node.js 22+, API User   |
| Forms Developer MCP    | Developers using Umbraco Forms    | Umbraco Forms, Node.js 22+, API User    |

The Automate, Engage, and Forms servers automatically chain to the CMS Developer MCP Server. This gives your AI agent access to both product-specific and CMS tools in a single session.


---

# 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.umbraco.com/umbraco-in-ai/mcp/mcp-servers.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.