Search for stops by name or ID.
AI agents call search_stops_tool to retrieve information from CATA Bus 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 bus stop information based on user input. It performs a read-only query against a public transit database with no ability to modify, delete, or execute commands. The blast radius of misuse is minimal—an attacker cannot harm systems, commit fraud, or irreversibly alter data through search queries alone.
From the tool's definition Tool description states 'Search for stops by name or ID' — a retrieval operation with no modification or side effects. Sibling tools confirm this is a transit information server; search_stops_tool queries public bus stop data.
Attacks that exploit this kind of access
Search for stops by name or ID. It is categorised as a Read tool in the CATA Bus MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CATA Bus MCP Server MCP server in PolicyLayer and add a rule for search_stops_tool: 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 CATA Bus MCP Server. Nothing to install.
search_stops_tool 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_stops_tool 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_stops_tool. 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_stops_tool is provided by the CATA Bus MCP Server MCP server (pranav-karra-3301/catabus-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 →