Search for animals in Taipei Zoo by name (Chinese or English). Returns location, facts, and image URL.
AI agents call search_animal to retrieve information from Taipei Zoo Guide (mcp-tw-zoo) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about animals from a public dataset. It is a straightforward search/query operation with no capability to create, modify, delete, or execute external operations. The data returned is read-only informational content about zoo animals.
From the tool's definition Tool 'search_animal' performs a search query that 'returns location, facts, and image URL' — it retrieves and queries data without modifying or deleting anything. The description indicates no side effects.
Attacks that exploit this kind of access
Search for animals in Taipei Zoo by name (Chinese or English). Returns location, facts, and image URL. It is categorised as a Read tool in the Taipei Zoo Guide (mcp-tw-zoo) MCP Server, which means it retrieves data without modifying state.
Register the Taipei Zoo Guide (mcp-tw-zoo) MCP server in PolicyLayer and add a rule for search_animal: 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 Taipei Zoo Guide (mcp-tw-zoo). Nothing to install.
search_animal 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_animal 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_animal. 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_animal is provided by the Taipei Zoo Guide (mcp-tw-zoo) MCP server (simonliu-moltbot/mcp-tw-zoo). 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 →