search_by_city
AI agents call search_by_city to retrieve information from PostalDataPI 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 postal/location data based on city input. No indication of data creation, modification, deletion, code execution, or financial transactions. The empty description lowers confidence slightly, but the naming pattern and server context (query-based postal data API) strongly suggest a read operation. Low severity because postal code lookups have minimal blast radius if misused.
From the tool's definition Tool name 'search_by_city' indicates a lookup/search operation with no mutation described. Server description emphasizes 'lookups' and 'validation' as read-only operations.
Attacks that exploit this kind of access
search_by_city. It is categorised as a Read tool in the PostalDataPI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PostalDataPI MCP Server MCP server in PolicyLayer and add a rule for search_by_city: 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 PostalDataPI MCP Server. Nothing to install.
search_by_city 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_by_city 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_by_city. 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_by_city is provided by the PostalDataPI MCP Server MCP server (postaldatapi/postaldatapi-mcp). 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 →