Search for image assets that can be used in the design
AI agents call search_image to retrieve information from Pistachio MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves image assets for design purposes. It performs a search query and returns results without creating, modifying, deleting, executing code, or affecting financial systems. The operation is read-only with minimal blast radius if misused by an AI agent.
From the tool's definition The tool description states 'Search for image assets that can be used in the design' — a query operation with no side effects. The verb 'search' is typical of Read operations that retrieve or query data without modifying anything.
Attacks that exploit this kind of access
Search for image assets that can be used in the design. It is categorised as a Read tool in the Pistachio MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Pistachio MCP Server MCP server in PolicyLayer and add a rule for search_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 Pistachio MCP Server. Nothing to install.
search_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 search_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 search_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.
search_image is provided by the Pistachio MCP Server MCP server (jack-beanstalk-2022/pistachiomcp). 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 →