Skip to main content
For installation instructions, see the Quickstart.

​
Supported IDEs

Neptune MCP works with any JetBrains IDE that has AI Assistant:
  • IntelliJ IDEA
  • PyCharm
  • WebStorm
  • GoLand
  • PhpStorm
  • Rider
  • CLion
  • RubyMine
  • DataGrip
JetBrains AI Assistant requires a JetBrains AI subscription.

​
Configuration

JetBrains AI Assistant currently only supports stdio transport for MCP servers. HTTP/SSE transport is not natively supported.
Already use Claude Desktop? Click Import from Claude in the MCP settings to reuse your existing configurations.
For more details, see the official JetBrains MCP documentation.

​
Troubleshooting

  1. Open Settings (Cmd+, on macOS, Ctrl+Alt+S on Windows/Linux)
  2. Navigate to Tools → AI Assistant → Model Context Protocol (MCP)
  3. Click Add to add a new MCP server
Alternatively, type / in the AI Assistant chat and select Add Command.
Option 1: JSON configuration (recommended)
  1. Click Add → select As JSON
  2. Paste this configuration:
{
  "mcpServers": {
    "neptune": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/shuttle-hq/neptune-cli-python.git", "neptune", "mcp"]
    }
  }
}
On Windows:
{
  "mcpServers": {
    "neptune": {
      "command": "cmd",
      "args": ["/c", "uvx", "--from", "git+https://github.com/shuttle-hq/neptune-cli-python.git", "neptune", "mcp"]
    }
  }
}
Option 2: Manual configuration
  • Name: neptune
  • Command: uvx (or cmd on Windows)
  • Arguments: --from git+https://github.com/shuttle-hq/neptune-cli-python.git neptune mcp
On Windows, use:
  • Command: cmd
  • Arguments: /c uvx --from git+https://github.com/shuttle-hq/neptune-cli-python.git neptune mcp
  1. Set Level to “Global” to use Neptune across all projects
  2. Click Apply
The IDE can’t find the uv package manager.
  1. Install uv:
# macOS
brew install uv

# Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
  1. Restart the IDE
MCP support requires:
  1. JetBrains AI Assistant plugin installed
  2. Active JetBrains AI subscription
  3. Recent version of the IDE (2024.x or later)
Update your IDE and plugins if MCP options aren’t visible.
JetBrains doesn’t natively support HTTP transport, but you can use a proxy tool like mcp-remote to connect to remote MCP servers.Alternatively, you can run Neptune’s HTTP server locally and connect via a stdio proxy:
  1. Start the Neptune MCP server in HTTP mode:
uvx --from git+https://github.com/shuttle-hq/neptune-cli-python.git neptune mcp --transport=http
  1. The server runs at http://localhost:8001/mcp
  2. Use a stdio-to-HTTP proxy to connect JetBrains to this endpoint
If the MCP connection fails:
  1. Check that Python 3.13+ is installed
  2. Try running the command manually in terminal to see errors
  3. Restart the IDE after configuration changes

​
Verify Installation

To verify Neptune is working:
  1. Open AI Assistant chat
  2. Ask: “What Neptune tools do you have?”
  3. You should see a list including login, deploy_project, etc.

​
Next Steps

Quickstart

Continue with authentication and deploy your first app