A remote Google Images search server that lets an assistant fetch image results, thumbnails and source pages for a query, including reuse-licensed images.
What you can do
Search Google Images for a query and get twenty results per page, each with image URL, dimensions, thumbnail and source page, paging with a cursor until the last page (get_v2). Find images labelled for reuse, such as Creative Commons or public domain, with title, type, dimensions, thumbnails, source page and a cached copy, up to a chosen maximum (get_v1).
When to use it
Useful when an assistant needs to find images for a topic, gather candidate visuals with dimensions and source pages, or locate openly licensed images that can be reused.
Requirements
A remote streamable HTTP endpoint; no packages, environment variables or headers are declared. Each call is billed at 1 Credits, so a funded account is implied.
Before you install
Every call costs 1 Credits, so repeated paging or large result sets spend credit. Results come from Google Images and include third-party image URLs and source pages; check licensing before reuse, since only get_v1 filters for reuse-labelled images.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/com.jojapi%2Fgoogle-image-search/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
Google Images results for a query, twenty a page: for each image its URL, width and height, its thumbnail with width and height, and the page it is on. `response.next_cursor` fetches the next twenty (null after the last page). Billing per call: 1 Credits.
Parametersqrequiredhltbsnfprsafecursorfilter
get_v1
Search Reusable Images
Images labelled for reuse (Creative Commons, public domain), up to `max` (default 10, at most 200), under `response.images`: title, type, the image with its width and height, thumbnails, the page it is on and a cached copy. Search Images searches all images. Billing per call: 1 Credits.
Parametersmaxkeywordrequired
Version history
1
v1.0.0LatestSep 16, 2026
Score
83%
83% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
Reached in the last 30 daysRequired25 pts
Auth declaredRequired10 pts
Tools listedRequired15 pts
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
LicenseNot applicable
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.