JetBrains MCP Server Plugin
About
JetBrains MCP Server Plugin was a plugin that provided the server-side implementation of the Model Context Protocol (MCP) for JetBrains IDEs, enabling integration between Large Language Models (LLMs) and the IDE. It has been deprecated; the core functionality is now built into…
Details
- License
- Apache-2.0
Explore
- Seamless LLM integration with JetBrains IDEs
- Server‑side handling of MCP requests
- Extension point system for custom tool implementation
- Tool naming guidelines: lowercase, descriptive, optional underscores
- Response class for success/error (Response(result) / Response(error = message))
- Integration with JetBrains MCP Proxy
- Installation of JetBrains MCP Proxy
- JetBrains IDE (IntelliJ IDEA, WebStorm, etc.)
The plugin provides an extension point system that allows third-party plugins to implement their own MCP tools. Here's how to implement and register your custom tools.
Refer to the demo plugin to get started.
Your tool implementation should follow these guidelines:
- Tool names should be descriptive and use lowercase with optional underscores
- Create a data class for your tool's arguments that matches the expected JSON input
- Use the Response class appropriately:
- Response(result) for successful operations
- Response(error = message) for error cases
- Use the provided Project instance for accessing IDE services
JetBrains MCP (Model Context Protocol) Server Plugin enables seamless integration between Large Language Models (LLMs) and JetBrains IDEs. This plugin provides the server-side implementation for handling MCP requests and exposes extension points for implementing custom tools.
Prerequisites
- Installation of JetBrains MCP Proxy
- JetBrains IDE (IntelliJ IDEA, WebStorm, etc.)
Custom Tools Implementation
The plugin provides an extension point system that allows third-party plugins to implement their own MCP tools. Here's how to implement and register your custom tools.
Refer to the demo plugin to get started.
3. Tool Implementation Guidelines
Your tool implementation should follow these guidelines:
- Tool names should be descriptive and use lowercase with optional underscores
- Create a data class for your tool's arguments that matches the expected JSON input
- Use the Response class appropriately:
- Response(result) for successful operations
- Response(error = message) for error cases
- Use the provided Project instance for accessing IDE services
How to Publish Update
1. Updatesettings.gradle.kts to provide a new version
2. Create release on Github, the publishing task will be automatically triggered
Contributing
We welcome contributions! Please feel free to submit a Pull Request.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
