@houtini/gemini-mcp
io.github.houtini-ai/gemini · version 2.10.1 · 2,627 weekly npm downloads · audited 2026-11-03
Notes
Findings
No hidden-instruction or invisible-character findings in any tool, prompt, or resource description.
Claude Connectors Directory readiness
- ✅ Every tool has a title 14 of 14 tools
- ❌ Every tool declares readOnlyHint or destructiveHint Missing on 14 of 14: gemini_help, gemini_prompt_assistant, gemini_chat, gemini_list_models and 10 more
- ✅ Tool names are 64 characters or fewer All within limit
- ❌ Descriptions avoid instructions about model behavior or other tools 1 of 14 descriptions reference other tools or tell the model what it must do: load_image_from_path
- ✅ No hidden instructions or invisible characters in tool metadata None found
Checks the directory's published tool requirements that are visible from tools/list. Passing them does not guarantee acceptance.
Supply chain
- Install scripts: none
- npm provenance: no
- Source repository linked: yes
- License: Apache-2.0
- Direct dependencies: 9
Tools (14)
| Name | Title | Hint | Description |
|---|---|---|---|
gemini_help | Gemini MCP Help | none | Get comprehensive help about Gemini MCP features, settings, and best practices |
gemini_prompt_assistant | Image & Chart Prompt Assistant | none | 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), lig… |
gemini_chat | Gemini Chat | none | Chat with Google Gemini models. Grounded in Google Search by default, on gemini-4-argon (Gemini 4 Argon). DO NOT SET max_tokens - the server allocates the model's full output ceiling automatically. It is a cap, not consu… |
gemini_list_models | List Gemini Models | none | List available Gemini models and their descriptions |
gemini_deep_research | Gemini Deep Research | none | Conduct deep research on complex topics using iterative multi-step analysis with Gemini. Runs grounded search passes on a fast model, then synthesises them with Gemini 3.1 Pro. Default 2 passes (2-3 minutes); more passes… |
describe_image | Describe Image (Gemini Flash) | none | Analyze and describe one or more images using Gemini multimodal understanding. Returns a text description — no image is generated. Default model: gemini-3.8-flash. [MCP_RECOMMENDED_TIMEOUT_MS: 180000] |
analyze_image | Analyze Image | none | Analyze and extract information from one or more images using Gemini multimodal understanding. Returns a text analysis - no image is generated. Default model: gemini-3.1-pro-preview. DO NOT SET max_tokens - the server al… |
load_image_from_path | Load Image from File Path | none | 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_image | Generate Image with Gemini | none | 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 (Nano Banana Pro). |
edit_image | Edit Image with Gemini | none | 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 d… |
generate_landing_page | Generate Landing Page | none | 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. [MCP_RECOMMENDED_TIMEOUT_MS: 300000] |
generate_svg | Generate SVG Graphic | none | 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. [MCP_RECOMMENDED_TIMEOUT… |
generate_video | Generate Video | none | 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.… |
gemini_viewer_payload | Viewer payload (internal) | none | Internal helper used by the Gemini MCP App viewers to fetch their display data. Not for model use — it returns nothing useful outside the viewer iframe. |
Check your own setup
npx mcpvetter scan --liveBadge
Add this to a README:
[](https://mcpvetter.com/servers/houtini-gemini-mcp)Publish this server?
Get the MCPVetter verified badge, a re-audit within 24 hours of every npm release, and an email whenever tools, findings, or Claude directory readiness change. $29 per server per month. You prove ownership first, free.