[ MCP SERVER SUMMARY ]
JetBrains MCP server summary
JetBrains IDEs expose MCP capabilities so AI assistants can work with your open project — navigate code, run IDE actions, and use editor context. The legacy @jetbrains/mcp-proxy bridges STDIO clients to the IDE; newer IntelliJ-based IDEs (2025.2+) include built-in MCP. Bifrost can host the proxy connection so multiple agents share one governed IDE bridge.
| Property | Details |
|---|---|
| Company | JetBrains |
| Connection type | STDIO |
| Authentication | None (local IDE proxy) |
| Package or endpoint | @jetbrains/mcp-proxy |
| Capabilities | IDE project context, Editor and refactor actions, Local JetBrains tool bridge |
| Official documentation | JetBrains MCP documentation |
Before you start
- A JetBrains IDE with MCP Server support or plugin
- Node.js 18+ for the mcp-proxy package
What you can do with JetBrains
- Connect Claude Desktop or Cursor to IntelliJ/PyCharm through Bifrost
- Keep IDE automation available only to approved virtual keys
- Log IDE tool calls when agents refactor or run inspections
[ HOW TO CONNECT ]
Connect JetBrains to Bifrost in three steps
Install Bifrost
Start the gateway locally or deploy in your VPC.
npx -y @maximhq/bifrost
Add JetBrains in MCP Gateway
Open MCP Gateway in the Bifrost dashboard, click New MCP Server, and choose STDIO. Or register via the API below.
• Ensure the JetBrains IDE is running with MCP enabled before Bifrost connects.
• Prefer the built-in IDE MCP server on 2025.2+ when available; otherwise use @jetbrains/mcp-proxy.
• Optional env IDE_PORT / HOST can target a specific IDE instance.
Point clients at Bifrost /mcp
Configure Claude Desktop, Cursor, or Claude Code to use your Bifrost endpoint with a virtual key instead of connecting directly to JetBrains.
{
"mcpServers": {
"bifrost": {
"url": "http://localhost:8080/mcp",
"headers": {
"Authorization": "Bearer vk_your_virtual_key"
}
}
}
}[ EXAMPLE CONFIG ]
Register JetBrains via API
Add this MCP client with a POST to /api/mcp/client. See Connecting to MCP Servers for full options.
curl -X POST http://localhost:8080/api/mcp/client \
-H "Content-Type: application/json" \
-d '{
"name": "jetbrains",
"connection_type": "stdio",
"stdio_config": {
"command": "npx",
"args": [
"-y",
"@jetbrains/mcp-proxy"
]
},
"tools_to_execute": [
"*"
]
}'[ WHY BIFROST ]
Run JetBrains through one governed gateway
Access control
Virtual keys, RBAC, and tool allowlists per team or agent.
Cost governance
Attribute MCP tool spend alongside LLM usage in one view.
Observability
Log every tool call with latency, server, and virtual key metadata.
Credential isolation
Upstream secrets stay in the gateway — not on every laptop.
[ FAQ ]
Common questions
What does the JetBrains MCP server do?
JetBrains exposes ide project context, editor and refactor actions, local jetbrains tool bridge to MCP-compatible AI clients. Bifrost connects to it as an upstream MCP client and exposes approved tools through one governed /mcp endpoint.
How does JetBrains authenticate when used with Bifrost?
JetBrains uses None (local IDE proxy). Store credentials in Bifrost's environment or credential configuration so they stay at the gateway instead of being copied into every AI client.
Can Claude Desktop, Cursor, or Claude Code use JetBrains through Bifrost?
Yes. After registering JetBrains in Bifrost, point any HTTP MCP-compatible client at the Bifrost /mcp endpoint and authenticate with a virtual key. The client sees only the tools allowed for that key.
[ RELATED SERVERS ]
More MCP integrations
GitHub
GitHub's official MCP Server.
GitLab
GitLab's official MCP server enabling AI tools to securely access GitLab project data, manage issues, and perform repository operations via OAuth 2.0.
Context7
Provide AI coding assistants with current, version-specific library documentation and code examples through Context7.