# Google Lens

Google Lens searches an image for visual matches, products, and related content. Useful when an agent needs to identify objects or trace image context.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 387 installs
- Author: google
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/google/lens
- Updated: 2026-05-17
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/google-lens

## What it does

Google Lens adds the `lens_lookup` tool to an agent. It sends an image through Google Lens reverse search and returns visual matches, recognized products, and related content. That covers product identification, plant or animal lookup, and checks of where visual material may come from.

The server works with Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, and Gemini CLI. Connect it through the remote HTTP endpoint `https://lens--google.run.tools`. No API key is required; search data is provided through SerpAPI. Smithery has no affiliation with Google.

## Requirements
- Remote server: `https://lens--google.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http lens https://lens--google.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add google-lens --url https://lens--google.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "google-lens": {
            "url": "https://lens--google.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "google-lens": {
            "type": "http",
            "url": "https://lens--google.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http google-lens https://lens--google.run.tools
```

## When to use it
- identify a product from a photo
- look up a plant or animal in an image
- find visual matches for a picture
- trace the provenance of image content

## Example prompts
- Find visual matches for `product.jpg` and list similar products.
- Identify the plant or animal in `plant.png` and return related content.
- Use `lens_lookup` to investigate the source of `screenshot.png`.

## Similar
- [find-the-original-image](https://affpapa.org/en/nevibecode/skills/find-the-original-image.md) — skill · 56600 installs
- [HasData Google Images](https://affpapa.org/en/nevibecode/mcp/hasdata-google-images.md) — MCP server · ★ 5 repo stars
- [Google Local](https://affpapa.org/en/nevibecode/mcp/google-local.md) — MCP server · 729 installs
- [Google Flights](https://affpapa.org/en/nevibecode/mcp/google-google-flights.md) — MCP server · 289 installs
- [Google Jobs](https://affpapa.org/en/nevibecode/mcp/google-jobs.md) — MCP server · 122 installs
- [Google Finance](https://affpapa.org/en/nevibecode/mcp/google-finance.md) — MCP server · 1350 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
