GeminiBLOCK
Google Gemini MCP - Use Google's visual, video and chat capabilities in your AI Assistant. Uses MCP Apps to preview created images, landing pages, SVGs and video
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.npmjs.com/package/@houtini/gemini-mcp) [](https://registry.modelcontextprotocol.io) [](https://snyk.io/test/github/houtini-ai/gemini-mcp) [](https://opensource.org/licenses/Apache-2.0)
I've had this Gemini MCP server running in my Claude Desktop setup for the best part of a year now. It's one of the few I leave switched on permanently. Not because Gemini replaces Claude (it doesn't), but because grounded search, image generation, SVG diagrams and video are things Gemini happens to do well, and having them as tools inside Claude beats flipping between browser tabs.
Fourteen tools, built around the models people actually come looking for: Nano Banana Pro (gemini-3-pro-image) and Nano Banana 2 for images, Veo 3.1 for video with synchronised audio, and Gemini 3.1 Pro for chat and deep research with Google Search grounding. Everything previews inline in Claude Desktop through MCP Apps rather than landing as a file path you have to go and open.
One npx command. That's it.
Quick Navigation What it makes | Get started | What it does | [Image out
ca718bc131f1OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add gemini-mcp --env GEMINI_API_KEY=${GEMINI_API_KEY} -- npx -y @houtini/[email protected]Exposed tools (8)
8 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
analyze_image | read | |
describe_image | read | |
gemini_chat | read | |
gemini_deep_research | read | |
gemini_help | read | |
gemini_list_models | read | |
gemini_prompt_assistant | read | |
load_image_from_path | read |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | FAIL |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- declared (4 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (14)
register-viewer-payload.ts
viewer-payload-store.ts
logger.info(`Iteration ${i + 1} token usage`, {return `http://127.0.0.1:${this.port}/${this.token}`;const url = new URL(req.url || '/', `http://127.0.0.1:${this.port}`);? `http://127.0.0.1:${mediaServerPort}`readFileSync(new URL('../../package.json', import.meta.url), 'utf8')import { GeminiConfig } from '../../config/types.js';import { GeminiError } from '../../utils/error-handler.js';import { fetchWithRetry } from '../../utils/fetch-retry.js';import { GeminiConfig } from '../../config/types.js';@google/genai, @modelcontextprotocol/ext-apps, @modelcontextprotocol/sdk, @panzoom/panzoom, dotenv, sharp, winston, zod
assets/showcase/cockpit-veo.gif
image-embed.png
Gates applied: no_behavioural_pass.
ca718bc131f1full audit observations/trust-audit/mcp-server/houtini-ai__gemini-17.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | ca718bc131f1 | BLOCK | D | 69 | first audit |
Questions
What is the Gemini MCP server?
Google Gemini MCP - Use Google's visual, video and chat capabilities in your AI Assistant. Uses MCP Apps to preview created images, landing pages, SVGs and video
What tools does Gemini expose?
8 in total: 8 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Gemini safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Gemini need?
It reads GEMINI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Gemini run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @houtini/gemini-mcp at 2.9.0.
How current is this page?
The grade is for one exact copy of the source (ca718bc131f1), read on 2026-10-08. The repository is watched and re-audited when it changes.