gemini_version
Get cached Gemini CLI version information (30-minute TTL).
How to use it
gemini_version is exposed by the Gemini Cli MCP Server MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the gemini_version tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Gemini Cli MCP Server
claude mcp add gemini-cli /absolute/path/to/.venv/bin/python /absolute/path/to/mcp_server.py -s user -e GEMINI_API_KEY='YOUR_GEMINI_API_KEY'Other tools in Gemini Cli MCP Server (27)
Enhanced multi-platform AI collaboration with cross-platform capabilities.
Get cache statistics for all cache backends.
Clear/delete a specific conversation.
Execute any Gemini CLI command directly with comprehensive error handling.
Comprehensive code analysis with structured output (NEW).
Advanced multi-source content comparison and analysis (NEW).
Continue an existing conversation with context history.
Get conversation system statistics and health.
Compare responses across Gemini CLI and OpenRouter models with @filename support.
Evaluate Claude Code implementation plans (500,000 char limit).
Extract structured data using JSON schemas (NEW).
Get cached Gemini CLI help information (30-minute TTL).
List active conversations with metadata.
Get comprehensive server performance metrics and statistics.
List all available Gemini AI models.
List all available OpenRouter models (400+) with advanced filtering and output options.
Get responses from any of 400+ AI models via OpenRouter with @filename support.
Get OpenRouter usage statistics and costs for the current session.
Send prompts with structured parameters and validation (100,000 char limit).
Get comprehensive rate limiting and quota statistics.
Review specific code suggestions with detailed analysis (300,000 char limit).
Execute prompts in sandbox mode for code execution (200,000 char limit).
Start a new conversation with ID for stateful interactions.
Summarize content with focus-specific analysis (400,000 char limit).
File-based summarization optimized for @filename syntax (800,000 char limit).
Test OpenRouter connectivity and client functionality.
Comprehensive verification of complete solutions (800,000 char limit).