Introduction
AI Controls & Features
Migrating from Xamarin.Forms to .NET MAUI
Globalization and Localization
Knowledge Base
API Reference
AI Coding Assistant / Getting Started
New to Telerik UI for .NET MAUI? Start a free 30-day trial

Getting Started with the Telerik UI for .NET MAUI AI Coding Assistant (MCP Server)

Updated on Feb 16, 2026

The Telerik MAUI MCP (Model Context Protocol) server enhances your AI-powered development experience by providing specialized context about Telerik UI for .NET MAUI components.

This MCP server enables AI-powered IDEs and tools to generate more accurate, tailored code that leverages Telerik UI for .NET MAUI components and APIs. You can ask complex questions about Telerik components, request specific implementations, and generate comprehensive code solutions.

The Telerik MAUI MCP server works in Chat (Ask) and Agent modes.

Prerequisites

To use the Telerik MAUI MCP server, you need:

Installation

Depending on your environment, you can install the Telerik MAUI MCP server in any of the following ways:

  • By using the dnx script (.NET 10 or later only) or the dotnet CLI (.NET 9):

    bash
    dnx Telerik.MAUI.MCP

  • By using npm:

    bash
    npm i @progress/telerik-maui-mcp

Next, make sure the configuration in your mcp.json is correct, and then add your Telerik license.

Configuring mcp.json

Use the settings in the following table to configure the Telerik MAUI MCP server in the mcp.json file of your code editor. Select the correct value based on your development environment.

Setting Name.NET 10 Value.NET 9 ValueNode.js Value
Package Name"Telerik.MAUI.MCP""Telerik.MAUI.MCP""@progress/telerik-maui-mcp"
Type"stdio""stdio""stdio"
Command"dnx""dotnet""npx"
Arguments"Telerik.MAUI.MCP", "--yes""tool", "run", "telerik-maui-assistant""-y"
Server Name"telerik-maui-assistant""telerik-maui-assistant""telerik-maui-assistant"

Configuring Your License

An active Telerik UI for .NET MAUI license is required to use the Telerik MAUI MCP server.

  • When installing the MCP server by using the .NET tooling (dnx or dotnet tool install), the license key file will be retrieved automatically if it is present in the default directory on your system (%AppData%\Telerik\telerik-license.txt on Windows and ~/.telerik/telerik-license.txt on Linux.). No additional action is required.

  • When using the .NET tooling, but your license key file is not in the default directory, use one of the options below.

  • When using Node.js, add your license key file as an environment variable in your mcp.json file using one of the options below:

    • As a license file path (recommended)

      json
      "env": {
    "TELERIK_LICENSE_PATH": "THE_PATH_TO_YOUR_LICENSE_FILE"
}

    • As a license key value

      json
      "env": {
    "TELERIK_LICENSE": "YOUR_LICENSE_KEY_HERE"
}

Using a license file path is recommended unless you're sharing settings across different systems. Remember to update your license key when necessary.

MCP Clients Configuration

Below you can find installation tips and MCP server configuration for some popular MCP clients.

Visual StudioVisual Studio CodeCursor
  • Early Visual Studio 17.14 versions require the Copilot Chat window to be open when a solution loads for the MCP server to work properly.
  • For complete setup instructions, see Use MCP servers in Visual Studio.

  1. Add an .mcp.json file to either of the following locations:

    • For a workspace-specific setup, add the file to the solution's folder.
    • For a global setup, add the file to your user directory, %USERPROFILE% (for example, C:\Users\YourName\.mcp.json).
    json
    {
  "servers": {
    "telerik-maui-assistant": {
      "type": "stdio",
      "command": "dnx",
      "args": ["Telerik.MAUI.MCP", "--yes"],
    }
  }
}

  2. Restart Visual Studio.

  3. Enable the Telerik MAUI MCP server in the Copilot Chat window's tool selection dropdown.

The basic setup in Visual Studio Code involves the following steps:

  1. Enable chat.mcp.enabled in the Visual Studio Code settings.

  2. Create a .vscode/mcp.json file in your workspace root (or user folder for global setup):

    json
    {
  "servers": {
    "telerik-maui-assistant": {
      "type": "stdio",
      "command": "dnx",
      "args": ["Telerik.MAUI.MCP", "--yes"],
    }
  }
}

  3. For global discovery, enable chat.mcp.discovery.enabled in settings.json:

    json
    {
  "chat.mcp.discovery.enabled": true
}

  4. Restart Visual Studio Code.

For complete setup instructions, see Model Context Protocol.

Create a .cursor/mcp.json file in your workspace root (or user folder for global setup):

json
{
  "mcpServers": {
    "telerik-maui-assistant": {
      "type": "stdio",
      "command": "dnx",
      "args": ["Telerik.MAUI.MCP", "--yes"],
    }
  }
}

Troubleshooting

Known Issue: Hanging tool calls in Visual Studio

When using Telerik AI tools in Visual Studio, GitHub Copilot may:

  • hang during tool invocation;
  • show UI for a successful tool response, but actually fail silently;
  • continue generation without waiting for parallel tool calls.

In these cases, the response may be generated but not provided to the Copilot Agent UI.

This is a known issue in Visual Studio Copilot, not related to Telerik MCP servers or AI tools, and does not reproduce in VS Code.

For more details, see the related Visual Studio Developer Community issue:
https://developercommunity.visualstudio.com/t/Copilot-stopped-working-after-latest-upd/10936456

Microsoft has acknowledged the issue and marked it as Fixed - Pending Release. A future Visual Studio update is expected to resolve it.

Usage

By default, MCP clients do not call MCP tools in a deterministic way. Some MCP clients like VS Code allow you to explicitly reference the desired MCP tool in your prompt.

To use the Telerik MAUI MCP server:

  1. Start your prompt with one of these triggers:

    • #telerik
    • #telerikmaui
    • #telerik-maui-assistant

  2. Verify server activation by looking for these messages:

    • Visual Studio: Running telerik-maui-assistant
    • Visual Studio Code: Running telerik-maui-assistant
    • Cursor: Calling MCP tool telerik-maui-assistant

  3. Grant permissions when prompted (per session, workspace, or always).

  4. Start a fresh session for unrelated prompts to avoid context pollution.

  5. Use in Chat (Ask) and Agent modes.

Improving Server Usage

To increase the likelihood of the Telerik MAUI MCP server being used, add custom instructions to your AI tool:

Sample Prompts

The following examples demonstrate useful prompts for the Telerik MAUI MCP server:

  • "#telerik-maui-assistant Create new maui project with Telerik. Add sample usage of the DataGrid component."
  • "#telerik-maui-assistant Create a DataGrid with 3 columns - Name, Country, City. Add the corresponding business object in the code behind and populate it with sample data. Add 20 entries to the data."
  • "#telerik-maui-assistant Add CollectionView. Enable drag and drop operation in the control."

Number of Requests

A Telerik Subscription license is required in order to use the Telerik MAUI AI Coding Assistant. Trial users can make a limited number of requests per year.

Local AI Model Integration

You can use the Telerik MAUI MCP server with local large language models (LLMs):

  1. Run a local model, for example, Ollama.
  2. Use a bridge package like MCP-LLM Bridge.
  3. Connect your local model to the Telerik MAUI MCP server.

This setup allows you to use the Telerik AI Coding Assistant without cloud-based AI models.

See Also

In this article
PrerequisitesInstallationConfiguring mcp.jsonConfiguring Your LicenseMCP Clients ConfigurationTroubleshootingUsageImproving Server UsageSample PromptsNumber of RequestsLocal AI Model IntegrationSee Also
Not finding the help you need?
Contact Support