Gemini-Eyes
MCP bridge to gemini.google.com: vision analysis of images and videos, Imagen image and Veo video generation, and conversation management using the logged-in browser session with no API key.
接入 gemini.google.com 的 MCP 桥:图片/视频视觉识别、Imagen 生图、Veo 生视频与历史对话管理,复用浏览器登录态,无需 API Key。
How to install
dsh plugin add github:ConsoleSun/Gemini-Eyes About
gemini-web-mcp **让 Agent 用上 Gemini 的「眼睛」和「手」** —— 一个 MCP 服务,把 gemini.google.com 网页端的能力桥接给任何 Agent: 🗣️ **对话**:多轮聊天、续聊历史会话 👁️ **看图 / 看视频**:上传本地文件,让 Gemini 识别并描述 🎨 **生图(Imagen)/ 🎬 生视频(Veo)**:自动下载成品到本地 💬 **会话管理**:列出 / 读取 / 删除账号下的历史对话 🔄 **免维护登录态**:后台每 25 分钟自动续期 Cookie,服务常驻就不过期 **核心特点**:不走官方 API——**不需要 API Key、不产生 API 计费**。它复用你浏览器里 已登录的 Google 会话 Cookie,重放网页端的内部请求,与你在浏览器里使用完全等价 (共享账号历史、共享生成额度)。 ## ⚠️ 风险提示 > 本项目是对 Gemini 网页端内部接口的逆向封装,非官方 API;自动化访问可能违反 Google 服务条款,请合法使用、自行评估风险。**请务必使用专用 Google 小号测试, 不要使用主力账号**——这类操作有真实的封号风险,且不应用于商业用途或批量抓取。 --- 快速开始 环境:Python ≥ 3.10,推荐 uv。 bash uv sync --extra de…
Recommendation signals
Meta
- License
- –
- Language
- Python
- GitHub stars
- 11
- mo. downloads
- –
- Last push
- 2026-08-24
- Created
- 2026-08-14
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令;无 license
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- agent, deepseek-harness, dsh-plugin, gemini, mcp
Related plugins
modlens
liustack/modlens
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
dsh-web
zhu1090093659/dsh-web-ui/tree/main/packages/dsh-tool-describe-image
A `describe_image` vision tool for text-only models: images (local path, URL, attachment) go to a configurable OpenAI-compatible vision endpoint and only the returned text enters the session.
dsh-vision-router
ysr666/dsh-vision-router
Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.
dsh-vision-toolkit
Anionex/dsh-vision-toolkit
Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.