Get comprehensive help about Gemini MCP features, settings, and best practices

Get expert prompt templates and guidance for Gemini image generation. Covers photography (portraits, products, cinematic), chart/diagram design (9 professional design systems including FT, Bloomberg, Tufte, Du Bois), lighting, colour grading, lens simulation, and style aesthetics. For charts: use chart_design with a color_scheme to get a full professional design system prompt.

Chat with Google Gemini models

List available Gemini models and their descriptions

Conduct real Deep Research on complex topics: Google's autonomous Deep Research agent does multi-step live web search and returns a synthesised, cited report (takes several minutes). Runs the actual Deep Research agents via the Gemini Interactions API. [MCP_RECOMMENDED_TIMEOUT_MS: 900000]

Analyze and describe one or more images using Google Gemini image models (Nano Banana Pro). Returns a text description — no image is generated. Default model: gemini-3-flash-preview.

Analyze and extract information from one or more images using Gemini multimodal understanding. Returns a text analysis — no image is generated. Default model: gemini-3-pro-preview.

Read a local image file and return it as base64-encoded data ready to pass to generate_image, edit_image, describe_image, or analyze_image tools. Supports JPEG, PNG, GIF, WebP, BMP.

Generate an image using Google Gemini image models (Nano Banana Pro). Returns image with inline preview in Claude Desktop and saves full-resolution to disk. Default model: gemini-3-pro-image-preview.

Edit one or more images using Google Gemini image models (Nano Banana Pro). Provide images and natural-language instructions for how to modify them. Returns edited image with inline preview and saves full-resolution to disk.

Generate a complete, self-contained HTML landing page using Gemini. Returns inline preview with responsive viewport controls. No external dependencies; inline CSS and vanilla JS only.

Generate scalable vector graphics (SVG) using Gemini. Creates clean, production-ready SVG code for diagrams, illustrations, icons, and data visualizations. Returns inline preview with SVG viewer.

Generate videos using Google Veo 3.1 AI model. Creates realistic 4-8 second videos from text prompts with optional first-frame image and reference images for character/style consistency. Supports native audio generation. Processing time: 2-5 minutes for 1080p videos. Returns video file path with optional thumbnail and HTML preview player. ⚠️ IMPORTANT: Video generation is ASYNC and takes 2-5 minutes. The tool will poll for completion automatically.

Delegate a task to an autonomous Gemini agent (via the agy CLI). Unlike gemini_chat (a single text response), the agent can read and edit files and run shell commands inside a working directory to actually carry out multi-step work, then returns its final report. Use it to offload self-contained coding/research/automation tasks. Returns a conversation_id you can pass back to continue iterating with the same agent. Pick a "Flash" model for speed, a "Pro" model for harder reasoning (see gemini_agent_models).

List the model labels available to the Gemini agent (gemini_agent). These come from agy models and differ from the API models in gemini_list_models — use the exact label as the agent's "model".

Extract text verbatim from images or PDFs using Gemini multimodal OCR. Returns the raw text (as Markdown for structure) — no summarising or analysis. For documents/PDFs, MEDIUM resolution gives the same OCR quality at half the token cost.

Summarise text or a local file with Gemini. Provide text, or file_path to almost any file: text/code, PDF, images, audio or video (Office docs must be exported to PDF first). Choose the length and optionally a focus or output language.

Transcribe speech from an audio or video file to text using Gemini. Optional timestamps, speaker labels (diarization) and language hint. Provide a local file_path (loaded server-side) or inline base64 data.

Extract structured JSON from text or almost any local file (text/code, PDF, image, audio, video) using Gemini JSON mode. Describe the fields you want in instructions, optionally constrain the output with a json_schema (Gemini/OpenAPI subset). Returns parsed JSON.