DevExpress MCP Server: Configure Your AI-powered Coding Assistant
- 4 minutes to read
The DevExpress MCP Server connects GitHub Copilot and other AI assistants directly to DevExpress documentation. This connection enables accurate code generation based on official documentation without leaving the IDE.
Benefits of the DevExpress MCP Server
Once you configure the DevExpress MCP Server in your IDE, AI Assistants in Agent mode can help with the following tasks:
- Get accurate answers to DevExpress-related questions.
- Generate code based on official DevExpress documentation.
Important
Always review AI-generated output. Check for architectural issues, security vulnerabilities, and compliance with project standards. Output quality can vary depending on the prompt, AI model, and clarity of the project code.
Prerequisites
Supported IDEs and Platforms:
- Visual Studio 2022 (version 17.14 or later)
- Visual Studio 2026
- Visual Studio Code
- Cursor IDE
- JetBrains Rider 2025.1+
- GitHub (repository-level configuration)
Coding Assistants and AI Tools:
- GitHub Copilot
- JetBrains AI Assistant
- Claude Desktop
- Claude Code (CLI)
- GitHub Copilot CLI
- OpenAI Codex
- ChatGPT (Plus, Team, or Enterprise)
- Gemini CLI
- Other MCP-compatible AI Assistants
Common Setup Steps
- Enable Agent Mode: Your IDE may require that you activate Agent mode for MCP server integration. Check IDE documentation.
Configure DevExpress MCP Server: Add the server endpoint (
https://api.devexpress.com/mcp/docs) to the MCP configuration. The endpoint always accesses documentation for the latest version. Use a?v=parameter to target an earlier release (v24.2 or later).You can register the server in one of the following ways:
- Automatic registration: DevExpress Unified Component Installer or Template Kit.
- One-click installation: Visual Studio, VS Code, and Cursor.
- Manual installation: All supported IDEs and AI tools.
- Verify Connection: Confirm that the following DevExpress tools appear in your AI assistant’s available tools list:
devexpress_docs_search— performs semantic search across the documentation database and returns the top five matches.devexpress_docs_get_content— downloads complete help topics by URL.
- Specify Custom Instructions (optional): Define prompts that optimize how the AI assistant uses DevExpress tools. See the following section for additional information: Optimize Your AI Assistant.
Register the MCP Server Using DevExpress Wizards
DevExpress Unified Component Installer
DevExpress Unified Component Installer v26.1.5+ can register the DevExpress MCP Server in AI coding tools installed on your machine. Select the DevExpress Documentation MCP Server checkbox on the product selection page. If you run the installer in silent mode, use the /MCP switch.
The installer registers the server for the current Windows user in the following AI tools:
- GitHub Copilot in Visual Studio 2022 and Visual Studio 2026
- GitHub Copilot in Visual Studio Code
- GitHub Copilot CLI
- JetBrains Rider AI Assistant
- Cursor
- OpenAI Codex (CLI, IDE extension, and desktop app)
- Claude Desktop
- Claude Code
After installation, restart your IDE or AI tool and verify the connection. For additional information, refer to the following help topic section: DevExpress MCP Server — DevExpress Unified Installer.
DevExpress Template Kit
If you use the DevExpress Template Kit to create a new project in Visual Studio or VS Code, select the Use DevExpress MCP option. The Template Kit registers the MCP Server for the newly created project.
One-Click Installation Links
Use the following links for quick installation:
Note
If you experience issues with a one-click installation link, follow manual installation instructions listed in the next section.
Manual Installation and Optimization
For IDE-specific setup instructions (Visual Studio, VS Code, Cursor, JetBrains Rider, Claude, ChatGPT, Gemini CLI, and other AI tools), refer to the following article:
To get the most from the DevExpress MCP Server, define custom instructions that tell your AI assistant how to use DevExpress tools effectively. Setup examples are available for all supported IDEs:
Ask a Question: Best Practices
Follow these practices to get the most relevant answers from the DevExpress MCP Server:
- Name the component: Use exact class names (for example,
GridControlorDxPivotTable). - Name the platform: Specify the platform (for example, WinForms, WPF, Blazor, ASP.NET Core, or VCL).
- Ask for code: Request implementation examples explicitly.
- Reference dxdocs: Add “Use dxdocs” or “search DevExpress docs” to your prompt.
- Specify the version: If you use an older release, include the version (for example, “v24.2”).
The following prompts apply these best practices:
- Show me how to implement master-detail reports using DevExpress Reports for ASP.NET Core. Search DevExpress docs.
- Create a DxReportViewer with AI-powered features. Query dxdocs for best practices.
- How do I create a custom parameter in End-User Report Designer for WinForms? Use dxdocs.