Find pets by tags
AI agents call find_pets_by_tags to retrieve information from Petstore 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 or searches for pet records based on tag criteria. It is a read-only operation that queries existing data without creating, modifying, or deleting anything. The action 'find' is a classic read operation. Severity is low because querying pet data has minimal blast radius even if called inappropriately by an agent.
From the tool's definition Tool name 'find_pets_by_tags' and description 'Find pets by tags' indicate a search/query operation with no modification of data.
Attacks that exploit this kind of access
Find pets by tags. It is categorised as a Read tool in the Petstore MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Petstore MCP Server MCP server in PolicyLayer and add a rule for find_pets_by_tags: 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 Petstore MCP Server. Nothing to install.
find_pets_by_tags 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 find_pets_by_tags 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 find_pets_by_tags. 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.
find_pets_by_tags is provided by the Petstore MCP Server MCP server (raghavendraprakash/mcpforrestapis). 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 →