> 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/connect-to-an-mcp-server.md).

# Connect to an MCP Server

Connect an AI client to an Umbraco MCP server, either as a hosted remote service or as a local process.

Umbraco MCP servers support two connection modes. Choose the one that matches how your MCP server is deployed.

<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>Hosted MCP Setup</strong></td><td>Connect to a remote MCP server over HTTP. Authenticate with your Umbraco backoffice credentials through an OAuth login flow.</td><td></td><td><a href="https://docs.umbraco.com/umbraco-in-ai/mcp/connect-to-an-mcp-server/hosted-mcp-setup.md">Hosted MCP Setup</a></td></tr><tr><td><strong>Local MCP Setup</strong></td><td>Run an MCP server as a local Node.js process over stdio. Authenticate using a dedicated Umbraco API user.</td><td></td><td><a href="https://docs.umbraco.com/umbraco-in-ai/mcp/connect-to-an-mcp-server/local-mcp-setup.md">Local MCP Setup</a></td></tr></tbody></table>

## Hosted vs Local

With a hosted MCP server, the server runs as a remote service — either on Umbraco's shared Cloud infrastructure or on your own deployment. Your AI client connects to it over HTTP using a URL. Authentication is handled through an OAuth login using your existing Umbraco backoffice account.

With a local MCP server, the server runs as a Node.js process on your machine. Your AI client connects to it directly over stdio. Authentication uses a dedicated [API User](https://docs.umbraco.com/umbraco-cms/fundamentals/data/users/api-users) created in Umbraco.

|                                  | Hosted                                  | Local                                |
| -------------------------------- | --------------------------------------- | ------------------------------------ |
| Transport                        | HTTP (SSE or Streaming)                 | stdio                                |
| Authentication                   | OAuth — your Umbraco user account       | API User credentials                 |
| Tools available                  | Scoped to your Umbraco user permissions | Scoped to the API user's permissions |
| Works with web-hosted AI clients | Yes (ChatGPT, Claude.ai)                | No                                   |
| Requires Node.js locally         | No                                      | Yes (version 22+)                    |

Not all MCP servers support both modes. Check the documentation for the server you are using.


---

# 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/connect-to-an-mcp-server.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.
