Skip to main content
Use tk with Gemini Code Assist to manage issues from Google’s AI coding assistant in VS Code, JetBrains, and the Gemini CLI.

​
What is Gemini Code Assist?

Gemini Code Assist is Google’s AI coding assistant with agent mode capabilities. It integrates into VS Code, JetBrains IDEs, and Android Studio, and supports MCP servers for extending its tool access. The Gemini CLI provides a terminal-based interface with the same MCP support.

​
MCP Integration (VS Code)

Install the ticket-mcp MCP server to give Gemini Code Assist direct access to your issues.

​
Workspace Configuration

Create .gemini/settings.json in your project root: 
{
  "mcpServers": {
    "ticket-mcp": {
      "command": "uvx",
      "args": ["ticket-mcp"]
    }
  }
}

​
User-Level Configuration

For access across all projects, create or edit ~/.gemini/settings.json: 
{
  "mcpServers": {
    "ticket-mcp": {
      "command": "uvx",
      "args": ["ticket-mcp"]
    }
  }
}
After saving, reload VS Code with Developer: Reload Window from the Command Palette.
uv installed via: curl -LsSf https://astral.sh/uv/install.sh | shPython version 3.10 or higher (installed automatically by uv)Gemini Code Assist extension installed in VS Code

​
MCP Integration (JetBrains)

For IntelliJ IDEA, PyCharm, WebStorm, and other JetBrains IDEs (2025.1+):
  1. Go to Settings > Tools > AI Assistant > Model Context Protocol (MCP)
  2. Click + to add a new server
  3. Enter the configuration:
    • Name: ticket-mcp
    • Transport: STDIO
    • Command: uvx
    • Arguments: ticket-mcp
  4. Click Apply
JetBrains AI Assistant can also import MCP configurations from Claude Desktop. If you already have ticket-mcp configured there, click Import from Claude.

​
MCP Integration (Gemini CLI)

For the terminal-based Gemini CLI, add to ~/.gemini/settings.json: 
{
  "mcpServers": {
    "ticket-mcp": {
      "command": "uvx",
      "args": ["ticket-mcp"]
    }
  }
}
Verify with the /mcp command inside a Gemini CLI session to check that ticket-mcp tools are available.

​
Workflow Tips

​
Starting a Session

Ask Gemini: “Run tk triage and show me what I should work on today”

​
Creating Issues

Ask Gemini: “Create a high-priority bug for the broken API endpoint” Gemini will run: 
tk create "Fix broken API endpoint" -t bug -p 1

​
Closing Work

Ask Gemini: “Resolve tk-abc123, the fix is deployed”

​
Dependency Management

Ask Gemini: “Show the dependency tree for tk-xyz789 and explain the critical path”

​
Project Health

Ask Gemini: “Run tk insights and summarize the project health”

​
Troubleshooting

Ensure you’ve saved the config to .gemini/settings.json (not .vscode/mcp.json — Gemini uses its own config). Reload VS Code after making changes.
Verify you’re on JetBrains 2025.1 or later. Ensure Codebase mode is enabled in the AI chat window — MCP calls only work with Codebase mode active.
Run /mcp in the Gemini CLI to check server status. Ensure uvx is in your PATH. Try restarting the CLI session.
Enable caching with tk cache info to verify the analytics cache is working. Cached responses return in under 10ms.

​
Next Steps

CLI Reference

Complete tk command documentation

MCP Server

Deep dive into MCP server capabilities

Graph Analytics

Learn about PageRank and dependency analysis

Gemini Docs

Official Gemini Code Assist documentation

​
Sources