Get one or more random photos from Unsplash, optionally filtered by search query or orientation. This tool is perfect for getting inspiration, placeholder images, or diverse photo content. You can narrow the selection with search terms. Args: - query (string, optional): Search terms to filter ran...
AI agents call unsplash_get_random to retrieve information from Unsplash MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and retrieves publicly available photo data from Unsplash. It has no side effects, cannot modify any state, and presents no financial implications. The worst-case misuse would be excessive API calls, but the tool itself performs only read operations. Severity is low due to minimal blast radius—returning random photos carries negligible risk.
From the tool's definition Tool retrieves random photos from Unsplash with optional filtering by search query or orientation. No description indicates any ability to modify, delete, or create data. Function is purely retrieval-based (get, search, retrieve pattern).
Attacks that exploit this kind of access
Get one or more random photos from Unsplash, optionally filtered by search query or orientation. This tool is perfect for getting inspiration, placeholder images, or diverse photo content. You can narrow the selection with search terms. Args: - query (string, optional): Search terms to filter random selection - orientation (string, optional): Filter by. It is categorised as a Read tool in the Unsplash MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Unsplash MCP Server MCP server in PolicyLayer and add a rule for unsplash_get_random: 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 Unsplash MCP Server. Nothing to install.
unsplash_get_random 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 unsplash_get_random 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 unsplash_get_random. 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.
unsplash_get_random is provided by the Unsplash MCP Server MCP server (mjordi/unsplash-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 →