About imagedata
imagedata is a local bridge to HasData’s Google Images search service, for clients that need structured image results. It supports search filters, regional settings and pagination.
Key features
- 01Google Images result retrieval
- 02Size, color and type filters
- 03SafeSearch and region settings
- 04Device selection and pagination
- 05Image URLs, thumbnails and dimensions
Use cases
- 01Find images matching a query
- 02Narrow results by size or type
- 03Retrieve results for a region
- 04Inspect image source pages and dimensions
MCP support
Exposes the upstream Google Images search tool to MCP clients and forwards calls to HasData, returning results unchanged.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
1Saved tool list · updated 2d ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| q | string | Yes | Search query term for retrieving image results. |
| gl | string | No | The two-letter country code for the country you want to limit the search to. Provide one exact documented value (245 allowed), e.g. `ac`, `af`. |
| hl | string | No | The two-letter language code for the language you want to use for the search. Provide one exact documented value (159 allowed), e.g. `af`, `ak`. |
| ijn | number | No | Page number for paginated results, where 0 is the first page. |
| tbs | string | No | `tbs` parameter for the Google Images API customizes image search results with various filters that can be combined using commas. Here are the available options: Image Size Filters: - `isz:l` - Search for large images. - `isz:m` - Search for medium images. - `isz:i` - Search for icon-sized images. - `isz:lt,islt:qsvga` - Filter for images larger than 400×300. - `isz:lt,islt:vga` - Filter for images larger than 640×480. - `isz:lt,islt:svga` - Filter for images larger than 800×600. - `isz:lt,islt:xga` - Filter for images larger than 1024×768. - `isz:lt,islt:2mp` - Filter for images larger than 1600×1200. - `isz:lt,islt:4mp` - Filter for images larger than 2272×1704. - `isz:ex,iszw:1000,iszh:1000` - Search for images exactly 1000×1000. Color Filters: - `ic:color` - Search for full-color images. - `ic:gray` - Search for black and white images. - `ic:specific,isc:red` (and other colors such as orange, yellow, green, etc.) - Search for images predominantly in specified colors. Image Type Filters: - `itp:face` - Search for images of faces. - `itp:photo` - Search for photographs. - `itp:clipart` - Search for clipart images. - `itp:lineart` - Search for line drawings. - `itp:animated` - Search for animated images (GIFs). |
| safe | enum | No | Adult Content Filtering option.active | off |
| uule | string | No | The encoded location parameter. |
| domain | string | No | Google domain to use. Default is google.com. Provide one exact documented value (195 allowed), e.g. `google.ac`, `google.ad`. |
| filter | number | No | Defines whether to enable or disable the filters for 'Similar Results' and 'Omitted Results'. Set to 1 (default) to enable these filters, or 0 to disable them. |
| location | string | No | Google canonical location for the search. |
| deviceType | enum | No | Specify the device type for the search.desktop | mobile | tablet |
Details
From the project READMEimagedata
imagedata is a small local bridge to the hosted HasData
Google Images MCP server, which returns Google Images
search results as JSON. Give it a query, and it fetches
that query's image results: for each image, the title,
the page it appears on, the direct image URL, a
thumbnail, its dimensions, the source name and its
position in the results. Searches can be shaped with
the tbs filter string (image size, dominant color,
and image type such as face, photo, clipart, line art
or animated), safesearch, the similar/omitted-results
filter toggle, a Google domain, country and language
codes, a canonical or encoded location, a device type,
and page-based pagination.
The bridge stores no results of its own. It serves the upstream server's tool list locally, exactly as captured from the live endpoint, and forwards each tool call upstream, returning the result untouched. The captured surface is a single read-only fetch: there is no write, messaging, or payment tool in it.
Tools
hasdata_google_images_images_getImageSearchResults— fetch one page of Google Images results. Required:q(the search term). Optional:location(Google canonical location),uule(encoded location parameter),domain(the Google domain to use, e.g.google.com),gl(two-letter country code),hl(two-letter language code),tbs(filter string combining size filters such asisz:l, color filters such asic:color, and type filters such asitp:photo),safe(active/off),filter(1 or 0: similar/omitted-results filtering),deviceType(desktop/mobile/tablet), andijn(page number, 0 is the first page). Returns each image with title, source page URL, direct image URL, thumbnail, dimensions, source name, and position.
Configuration
HASDATA_GOOGLE_IMAGES_MCP_URL(optional) — override the upstream endpoint. Defaults tohttps://mcp.hasdata.com/mcp?apis=google_images. (The override hook is this rebuild's own labelled reconstruction.)HASDATA_API_KEY(optional) — when set, every upstream request carries anx-api-key: <key>header, for the caller's own HasData API key. When it is not set, no key header is sent. (The header name and the env name are pinned by the original's registry record; forwarding the key from this env var is a labelled reconstruction — the original surface was captured keyless.)
Forwarding mechanics
On the first tool call the client opens a streamable
HTTP session with the upstream: a JSON-RPC
initialize request (protocolVersion 2025-03-26,
clientInfo name imagedata), then a
notifications/initialized notification, then the
tools/call request carrying the caller's arguments
unchanged. When the upstream answers initialize
with an Mcp-Session-Id header, that value rides on
every later request of the session, which is reused
for the life of the process. Replies may arrive as
plain JSON or as server-sent events; both are read.
Successful upstream results pass through verbatim,
including any isError flag the upstream sets.
Failures — a JSON-RPC error, a non-2xx status, an
unreadable response, or a request that cannot be
completed — come back as an isError result whose
text starts with imagedata error: (this rendering
is this rebuild's own labelled reconstruction).
CLI
The tool is also a subcommand taking one JSON argument string:
npx @reneturcios/imagedata hasdata_google_images_images_getImageSearchResults '{"q":"golden retriever puppies","tbs":"isz:l,ic:color,itp:photo","safe":"active"}'
npx @reneturcios/imagedata --version
Exit codes: 0 on success, 1 on an isError
result, 2 on a usage error.
MCP server
npx -y @reneturcios/imagedata mcp
MCP client config:
{
"mcpServers": {
"imagedata": {
"command": "npx",
"args": ["-y", "@reneturcios/imagedata", "mcp"]
}
}
}
Docker
docker run -i ghcr.io/cloudcorprecords/imagedata
docker run --rm ghcr.io/cloudcorprecords/imagedata --version
The container's default command is mcp, so the first
form is a stdio MCP server; any other arguments reach
the CLI normally.
Development
npm install
npm run build
npm test
npm run dev
The test suite runs entirely against a stubbed JSON-RPC upstream — no live network calls.
License
MIT — see LICENSE.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.