persist_image
Store image at URL to folder relative to current workspace. If targetPath does not exist, the tool will create it automatically.
LABSCO SUMMARY
The search result and the file on disk are one step apart.
Results come back a window at a time, with the count and start index on the call and safe search alongside them, so a broad query can be worked through in batches. Saving takes the chosen result's URL and a path relative to the workspace and creates the target folder when it is not there. There is no editing, resizing or metadata step here — the image lands as it was found.
What it is
A two-tool image server: a paged online image search with a safe-search setting, and a downloader that stores a result into the current workspace.
What you get
- Paged image search — a query with a result count and a start index, and a safe-search setting on the same call.
- Storage of an image from its URL to a folder relative to the current workspace, with the target path created automatically when it does not exist.
Requirements
An API key and a search engine ID for image search, supplied as API_KEY and SEARCH_ENGINE_ID, plus a workspace path the server may write into.
Setup effort
One command plus a key — npx -y @srigi/mcp-google-images-search, then supply credentials
USE CASES
01
Filling a slide deck with images without leaving the editor
A query returns a page of candidates, and the chosen result's URL is written into a folder inside the workspace, which the tool creates if it is not already there.
02
Working through a large result set a page at a time
The start index and result count move a window through the matches, with safe search on or off, so a broad query can be reviewed in batches.
2 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
search_image
Search the image(s) online
BEFORE YOU INSTALL
What to know first
Tools you get
2 tools when we connected. search_image returns 1 to 10 results per call (default 2) and persist_image refuses files over 10MB. The example config sets autoApprove for both tools, so saving files will not prompt you.
Requires
- npx on PATH
- Node.js v20
- API_KEY in your environment
- SEARCH_ENGINE_ID in your environment
Where it runs
Both documented clients run the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the 2 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y @srigi/mcp-google-images-searchMCP Clients
Cline, Windsurf
JSON
{
"mcpServers": {
"googleImagesSearch": {
"command": "npx",
"args": [
"-y",
"@srigi/mcp-google-images-search"
],
"env": {
"API_KEY": "<YOUR_API_KEY>",
"SEARCH_ENGINE_ID": "<YOUR_SEARCH_ENGINE_ID>"
},
"autoApprove": [
"search_image",
"persist_image"
]
}
}
}
