Search for images across the web, similar to Google Images. Use this when you need to find photos, illustrations, diagrams, charts, logos, or any visual content. Perfect for finding images to illustrate concepts, locating specific pictures, or discovering visual resources. Images are returned by ...
AI agents call search_images to retrieve information from Jina AI without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
gl | string | — | Country code, e.g., 'dz' for Algeria |
hl | string | — | Language code, e.g., 'zh-cn' for Simplified Chinese |
tbs | string | — | Time-based search parameter, e.g., 'qdr:h' for past hour, can be qdr:h, qdr:d, qdr:w, qdr:m, qdr:y |
query | string | — | Image search terms describing what you want to find (e.g., 'sunset over mountains', 'vintage car illustration', 'data visualization chart') |
location | string | — | Location for search results, e.g., 'London', 'New York', 'Tokyo' |
return_url | boolean | — | Set to true to return image URLs, title, shapes, and other metadata. By default, images are downloaded as base64 and returned as rendered images. |
Parameters from the server's own tool schema.
This tool retrieves image search results from the web—a pure read operation with no side effects. It does not execute code, modify data, delete content, or trigger financial transactions.
From the tool's definition Tool description states it "search[es] for images across the web" and returns images as "base64-encoded JPEG images." The verb "search" and the explicit retrieval function indicate data querying with no modification or execution of external operations.
Risk signalsAccepts freeform code/query input (query)
Documented attack patterns abuse exactly the kind of access search_images gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Jina AI, and nothing reaches the server without passing your rules. This is the rule we recommend for search_images:
{
"version": "1",
"default": "deny",
"tools": {
"search_images": {}
}
}search_images is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for images across the web, similar to Google Images. Use this when you need to find photos, illustrations, diagrams, charts, logos, or any visual content. Perfect for finding images to illustrate concepts, locating specific pictures, or discovering visual resources. Images are returned by default as small base64-encoded JPEG images. It is categorised as a Read tool in the Jina AI MCP Server, which means it retrieves data without modifying state.
search_images accepts 6 parameters: gl, hl, tbs, query, location, return_url. The full parameter table on this page comes from the server's own tool schema.
Register the Jina AI MCP server in PolicyLayer and add a rule for search_images: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Jina AI. Nothing to install.
search_images is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_images rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for search_images. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
search_images is provided by the Jina AI MCP server (jina). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Jina AI, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
21 Jina AI tools catalogued and risk-classified — across an index of 43,000+ MCP servers.