# Cursor

[Cursor](https://cursor.com/) is an AI-powered code editor built as a fork of Visual Studio Code. It enhances the familiar Visual Studio Code experience with conversational AI features that help you write, refactor, and understand code more efficiently.

{% hint style="info" %}
The examples below use the Developer MCP package (`@umbraco-cms/mcp-dev`). Replace the package name if you are using a different Umbraco MCP server.
{% endhint %}

## Getting started

1. Go to **Cursor Settings** -> **Tools & MCP** -> **Add Custom MCP**.

![MCP Panel](/files/4Nb4lqYAcnltWTDoCuhz)

2. Add the following code to the config file.

```json
{
  "mcpServers": {
    "umbraco-mcp": {
      "command": "npx", 
      "args": ["@umbraco-cms/mcp-dev@latest"],
      "env": {
        "NODE_TLS_REJECT_UNAUTHORIZED": "0",
        "UMBRACO_CLIENT_ID": "umbraco-back-office-mcp",
        "UMBRACO_CLIENT_SECRET": "1234567890",
        "UMBRACO_BASE_URL": "https://localhost:12345",
        "UMBRACO_INCLUDE_TOOL_COLLECTIONS": "document,media,document-type,data-type"
      }
    }
  }
}
```

Replace the `UMBRACO_CLIENT_ID`, `UMBRACO_CLIENT_SECRET`, and `UMBRACO_BASE_URL` values with your local connection details.

![MCP Panel Added](/files/fstTk4zv8oGlZq0uECfD)

* The warning above indicates that the number of tools exceeds the limit is expected behaviour.
* [Choose which tools or tool collections](/umbraco-in-ai/mcp/cms-developer-mcp/available-tools.md) you want to enable for your first task.

{% hint style="info" %}
Selecting only the tools you need helps keep your setup efficient and conversations with your AI assistant more focused.
{% endhint %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.umbraco.com/umbraco-in-ai/mcp/local-mcp-setup/cursor.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.