Google Images

MCP server for searching images with Google

typescript

8

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "srigi-mcp-google-images-search": {
      "command": "npx",
      "args": [
        "-y",
        "@srigi/mcp-google-images-search"
      ],
      "env": {
        "API_KEY": "your-google-api-key-here",
        "SEARCH_ENGINE_ID": "your-search-engine-id-here"
      }
    }
  }
}

You can search Google Images directly in chat and save selected results to your project with this MCP. It renders actual image results in conversation, making visual inspiration and asset gathering fast without leaving your IDE.

How to use

Set up the MCP in your IDE and configure it with your Google API credentials. Once activated, you can perform image searches from your chat, view the results as real images, and save chosen images straight into your project folders.

How to install

Prerequisites: Node.js v20 or newer and a compatible IDE (Cline or Windsurf). You also need a Google Custom Search Engine with Image Search enabled and a Google API key.

Create and configure the MCP as shown in the configuration snippet below. This runs the MCP via npx using the published package and passes your credentials as environment variables.

{
  "mcpServers": {
    "googleImagesSearch": {
      "command": "npx",
      "args": ["-y", "@srigi/mcp-google-images-search"],
      "env": {
        "API_KEY": "your-google-api-key-here",
        "SEARCH_ENGINE_ID": "your-search-engine-id-here"
      },
      "autoApprove": ["search_image", "persist_image"]
    }
  }
}

Notes on setup and credentials

Step-by-step credential setup (summarized): create a Google Custom Search Engine that searches the entire web and enables image search, then obtain the API key from Google Cloud Console. Keep the API key and Search Engine ID handy to configure the MCP.

Usage examples

Search for images: Ask your AI assistant to search for images, for example, “Find 5 images of F-22.”
Get more results: If you want additional images, say, “Find 5 more images.”
Save an image: To add an image to your project, request, “Save the 3rd image to the assets folder.”

Security and limits

The MCP includes path validation and MIME type checks, enforces a 10 MB size limit per image, and supports common formats like JPEG, PNG, GIF, WebP, and SVG. Use your own API key and restrict access to trusted environments.

Development notes

If you contribute, you can run the project locally with Node.js v20+, direnv, and PNPM v10. Copy the example environment file, install dependencies, and start development. Reload the MCP server after code changes to reflect updates.

Available tools

search_image

Find images using Google's vast database. Provide query and optional count, safety level, and startIndex for pagination.

persist_image

Download and save images to your project using the image URL and a target path.