Get a random photo optionally filtered by category
AI agents call get_random_photo to retrieve information from Multi-MCPs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves random photos from what is likely an image service (possibly Unsplash or similar via the Multi-MCP aggregation). It performs a query operation that returns data without side effects—no creation, modification, deletion, or execution of commands. The optional filtering by category does not change this classification as it remains a read-only retrieval operation.
From the tool's definition Tool name 'get_random_photo' and description 'Get a random photo optionally filtered by category' indicate data retrieval with no modification, deletion, or code execution.
Attacks that exploit this kind of access
Get a random photo optionally filtered by category. It is categorised as a Read tool in the Multi-MCPs MCP Server, which means it retrieves data without modifying state.
Register the Multi-MCPs MCP server in PolicyLayer and add a rule for get_random_photo: 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 Multi-MCPs. Nothing to install.
get_random_photo 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 get_random_photo 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 get_random_photo. 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.
get_random_photo is provided by the Multi-MCPs MCP server (taylorchen/muti-mcps). 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 →