MCP Server Plugin

🚀 JetBrains MCP Server Plugin

The JetBrains MCP (Model Context Protocol) Server Plugin enables seamless integration between Large Language Models (LLMs) and JetBrains IDEs. This plugin offers a server-side implementation for handling MCP requests and provides extension points for custom tool implementation.

🚀 Quick Start

Prerequisites

• Install JetBrains MCP Proxy
• JetBrains IDE (IntelliJ IDEA, WebStorm, etc.)

✨ Features

The plugin provides an extension point system that allows third - party plugins to implement their own MCP tools.

💻 Usage Examples

Custom Tool Implementation

The following are the steps to implement and register a custom tool:

1. Create a Custom Tool

Create a class that inherits from AbstractMcpTool:

class MyCustomTool : AbstractMcpTool<MyArgs>() {
    override val name: String = "myCustomTool"
    override val description: String = "Describe the functionality of your tool"

    override fun handle(project: Project, args: MyArgs): Response {
        // Implement your tool logic here
        return Response.ok("Result")
    }
}

// Define your parameter data class
@Serializable
data class MyArgs(
    val param1: String,
    val param2: Int
)

2. Register Your Tool

To register your tool, add it as an extension to plugin.xml:

<idea-plugin>
    <!-- Your plugin configuration -->
    <depends>com.intellij.mcpServer</depends>
    
    <extensions defaultExtensionNs="com.intellij.mcpServer">
        <mcpTool implementation="com.example.MyCustomTool"/>
    </extensions>
</idea-plugin>

3. Tool Implementation Guidelines

Your tool implementation should follow these guidelines:

• The tool name should be descriptive, using lowercase letters and optional underscores.
• Create a data class for your tool parameters that matches the expected JSON input.
• Use the Response class appropriately:
  • Use Response(result) for successful operations.
  • Use Response(error = message) for error cases.
• Use the provided Project instance to access IDE services.

📚 Documentation

How to Publish Updates

1. Update settings.gradle.kts to provide a new version.
2. Create a release on GitHub, and the release task will be triggered automatically.

💪 Contribution Guidelines

We welcome contributions! Please feel free to submit Pull Requests.