AI agents call ai_search_submit_image to retrieve information from Pipiads without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
image_url | string | — | Image URL to search (provide either image_url or image_data) |
image_data | string | — | Base64-encoded image data |
Parameters from the server's own tool schema.
Even though ai_search_submit_image only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Submit an image for AI-powered visual search. Returns image_id for subsequent queries. It is categorised as a Read tool in the Pipiads MCP Server, which means it retrieves data without modifying state.
ai_search_submit_image accepts 2 parameters: image_url, image_data. The full parameter table on this page comes from the server's own tool schema.
Register the Pipiads MCP server in PolicyLayer and add a rule for ai_search_submit_image: 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 Pipiads. Nothing to install.
ai_search_submit_image 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 ai_search_submit_image 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 ai_search_submit_image. 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.
ai_search_submit_image is provided by the Pipiads MCP server (pipiads-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →