$ loading_
Connect Gemini text, image, video, and transcription tools to any MCP client.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "Gemini MCP" yet — see the docs or source repo.
Using Gemini MCP, call the text generation, image generation, and audio transcription tools to: write a welcome message for my education app, create a flat-illustration homepage banner, and transcribe this meeting audio into Chinese text.
Returns ready-to-use text, generated image output, and a clearly structured Chinese transcript.
Use Gemini MCP image and video capabilities to create for a smart fitness product: 1) a product poster image, and 2) a 15-second feature demo video script or video output, with a modern, high-tech style.
Produces brand-fit visual assets for prototyping, pitching, or marketing experiments.
I want to use Gemini through an MCP client in one workflow: first summarize this long document, then write a social media promo post from the summary, and finally generate a matching image. Output each tool result step by step.
Delivers chained multi-step content outputs ready for direct use in automated workflows.
Analyze images with Gemini vision models and answer questions with less context overhead.
Use Gemini without API keys for research, analysis, and media generation.
Expose local Gemini CLI as an MCP server for prompting, search, and file ops.
Use natural language to calculate and read or write files.
Look up Gemini API docs and get ready-to-use code snippets fast.
Use Gemini CLI in Claude Desktop or Code via Google login.