> 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/17.latest/mcp/connect-to-an-mcp-server/local-mcp-setup.md).

# Local MCP Setup

Connect a local Umbraco MCP server to your AI development environment

These guides show how to connect a local Umbraco MCP server to each host application. The examples use the [Developer MCP](/umbraco-in-ai/17.latest/mcp/mcp-servers/cms-developer-mcp.md) package (`@umbraco-cms/mcp-dev`). If you are using a different Umbraco MCP server, replace the package name in the configuration.

## Before You Start

* **Node.js 22+** is required. Check your version by running `node -v` in your terminal.
* **Umbraco API User** — You need to create an [API User](https://docs.umbraco.com/umbraco-cms/fundamentals/data/users/api-users) in Umbraco before connecting. This user allows the MCP server to communicate securely with the Management API.

## Hosts

### [Claude Desktop](/umbraco-in-ai/17.latest/mcp/connect-to-an-mcp-server/local-mcp-setup/claude-desktop.md)

Getting started with Claude Desktop.

### [Claude Code](/umbraco-in-ai/17.latest/mcp/connect-to-an-mcp-server/local-mcp-setup/claude-code.md)

Getting started with Claude Code.

### [Cursor](/umbraco-in-ai/17.latest/mcp/connect-to-an-mcp-server/local-mcp-setup/cursor.md)

Getting started with Cursor.

### [GitHub Copilot](/umbraco-in-ai/17.latest/mcp/connect-to-an-mcp-server/local-mcp-setup/github-copilot.md)

Getting started with GitHub Copilot.

### [OpenAI Codex](/umbraco-in-ai/17.latest/mcp/connect-to-an-mcp-server/local-mcp-setup/openai-codex.md)

Getting started with OpenAI Codex.


---

# 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/17.latest/mcp/connect-to-an-mcp-server/local-mcp-setup.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.