What does the JetBrains MCP Proxy Server do?
It proxies requests from an MCP client to a JetBrains IDE, enabling the client to access IDE tools and features.
@JetBrains
Basic information
A model context protocol server to work with JetBrains IDEs: IntelliJ, PyCharm, WebStorm, etc. Also, works with Android Studio
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"jetbrains": {
"command": "npx",
"args": [
"-y",
"@jetbrains/mcp-proxy"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
The JetBrains MCP Proxy Server proxies requests from an MCP client to a JetBrains IDE. It is deprecated; the core functionality is built into all IntelliJ-based IDEs since version 2025.2.
Install the MCP Server plugin in the JetBrains IDE, then configure an MCP client (e.g., VS Code or Claude Desktop) to launch npx -y @jetbrains/mcp-proxy. Optionally set environment variables IDE_PORT, HOST, or LOG_ENABLED for custom connection settings.
It proxies requests from an MCP client to a JetBrains IDE, enabling the client to access IDE tools and features.
Node.js version 18 or later is required. Node 16 is not supported and will cause a `Cannot find module 'node:path'` error.
No, it is deprecated. The core functionality is now built into all IntelliJ-based IDEs since version 2025.2 and documented via official JetBrains help.
Enable "Can accept external connections" in the IDE debugger settings, then use the machine’s LAN IP and explicit port in the MCP configuration, e.g., `IDE_PORT=YOUR_PORT HOST=YOUR_LAN_IP npx -y @jetbrains/mcp-proxy`.
For bugs or feature requests related to the built-in MCP functionality, use the JetBrains YouTrack project with subsystem `{MCP (Model Context Protocol)}`.
AptiBuild AI — Career Intelligence MCP Server Structured career decision scaffolding for AI agents. Provides personality-conditioned business idea generation, official BLS OEWS wage data, FRED labor market signals, and
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R
Comments