Integrate search grounded Gemini output into your workflow.
Integrate search grounded Gemini output into your workflow. The gemini mcp mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 13 defined tools rather than through you.
I've been running this MCP server in my Claude Desktop setup for months. It's one of the few I leave on permanently — not because Gemini replaces Claude, but because grounded search, image generation, SVG diagrams, and video are things Gemini does genuinely well. Having them as tools inside Claude beats switching browser tabs.
@houtini/gemini-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
Everything the assistant can do here goes through one of these:
gemini_chat — Chat with Gemini 3.1 Pro. Google Search grounding on by default. Supports thinking_levelgemini_deep_research — Multi-step iterative research with Google Search. Synthesises comprehensive reportsgemini_list_models — Lists available models from the Gemini APIgemini_help — Documentation for all features without leaving Claudegemini_prompt_assistant — Expert guidance for image generation with 9 chart design systemsgenerate_image — Image generation with optional search grounding. Full-res saved to diskedit_image — Edit images with natural-language instructions. Multi-turn continuity via thought signaturesdescribe_image — Fast image descriptions using Gemini 3 Flashanalyze_image — Structured extraction and analysis using Gemini 3.1 Proload_image_from_path — Read a local image file and return base64 for any image toolgenerate_video — Video generation with Veo 3.1 — 4-8 seconds at up to 4K with native audiogenerate_svg — Production-ready SVG: diagrams, illustrations, icons, data visualisationsYou will need 2 environment variables: GEMINI_API_KEY, GEMINI_IMAGE_OUTPUT_DIR. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Gemini MCP's toolset — gemini_chat, gemini_deep_research, gemini_list_models and 10 more — is a fair guide to whether it matches your workflow.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| gemini_chat | Chat with Gemini 3.1 Pro. Google Search grounding on by default. Supports thinking_level |
| gemini_deep_research | Multi-step iterative research with Google Search. Synthesises comprehensive reports |
| gemini_list_models | Lists available models from the Gemini API |
| gemini_help | Documentation for all features without leaving Claude |
| gemini_prompt_assistant | Expert guidance for image generation with 9 chart design systems |
| generate_image | Image generation with optional search grounding. Full-res saved to disk |
| edit_image | Edit images with natural-language instructions. Multi-turn continuity via thought signatures |
| describe_image | Fast image descriptions using Gemini 3 Flash |
| analyze_image | Structured extraction and analysis using Gemini 3.1 Pro |
| load_image_from_path | Read a local image file and return base64 for any image tool |
| generate_video | Video generation with Veo 3.1 — 4-8 seconds at up to 4K with native audio |
| generate_svg | Production-ready SVG: diagrams, illustrations, icons, data visualisations |
| generate_landing_page | Self-contained HTML landing pages with inline CSS/JS |
{
"mcpServers": {
"gemini": {
"command": "npx",
"args": ["@houtini/gemini-mcp"],
"env": {
"GEMINI_API_KEY": "your-api-key-here"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| GEMINI_API_KEY | Credential the server authenticates with. | Yes |
| GEMINI_IMAGE_OUTPUT_DIR | Filesystem location the server is allowed to use. | Optional |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.