How to Search Images with Cursor Using MCP Tools

Development work sometimes has a visual dimension: UI components, asset selection, design references, brand research, competitor analysis. Cursor handles code well, but finding visual references normally means switching to a browser. Adding Google Image Search via AgentPatch lets Cursor pull visual information during a session without you leaving the editor.

Why This Matters

Front-end work, documentation, and brand alignment often require visual references. Finding those references typically means opening a browser, searching, deciding what’s relevant, and bringing the information back to your project. That context switch adds up.

When Cursor has image search as a tool, it handles that step itself. You describe what you’re looking for and it finds it, the same way it would search for a code example or documentation page.

Google Image Search also supports filters: image type, size, color, usage rights. The tool exposes these, which is useful when you need something specific like a transparent-background logo or a photo within a particular license.

Setup

The AgentPatch CLI is designed for AI agents to use via shell access. Install it, and your agent can discover and invoke any tool on the marketplace.

Install (zero dependencies, Python 3.10+):

pip install agentpatch

Set your API key:

export AGENTPATCH_API_KEY=your_api_key

Example commands your agent will use:

ap search "web search"
ap run google-search --input '{"query": "test"}'

Get your API key from the AgentPatch dashboard.

  1. Open Cursor Settings (Cmd+Shift+J on Mac, Ctrl+Shift+J on Windows/Linux).
  2. Navigate to the MCP section in the sidebar.
  3. Click Add new global MCP server.
  4. Cursor opens ~/.cursor/mcp.json. Add the AgentPatch server config:
{
  "mcpServers": {
    "agentpatch": {
      "url": "https://agentpatch.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
  1. Replace YOUR_API_KEY with your actual key from the AgentPatch dashboard.
  2. Save and restart Cursor. It discovers all AgentPatch tools automatically.

Example

You’re building a component library and want visual references for the documentation. In Cursor’s chat:

“I’m documenting a data table component. Find screenshots of well-designed data tables with filters and pagination as visual reference.”

Cursor searches Google Images through AgentPatch:

Searching for "data table UI component filters pagination design"...

Found relevant results:

1. Airtable grid view — inline filters, sticky header, pagination controls
   [image URL]

2. Linear issues list — clean row design, status badges, dense but readable
   [image URL]

3. Notion database view — toggleable column types, sort indicators
   [image URL]

Common patterns: sticky column headers, row hover states, pagination
or infinite scroll (not both), filter chips above the table.

Want me to use these as reference while building the component spec?

Cursor found relevant examples, extracted common design patterns, and offered to apply them directly to your task. That visual research loop normally costs several minutes of manual work.

For more practical tasks, image search is useful for finding public domain photos for test content, checking what competitor product pages look like, or locating official logos and brand assets.

“Find the official logos for Stripe, Plaid, and Square in SVG or PNG format so I can add them to the integrations page.”

Cursor searches and returns URLs for each. You stay in the editor the entire time.

Wrapping Up

Image search rounds out Cursor’s research capabilities beyond text. One AgentPatch connection gives access to Google Image Search, Google Search, Bing Search, and everything else on the marketplace. No extra setup per tool. Explore the full list at agentpatch.ai.

← Back to blog