hat_ara
AI agents call hat_ara to retrieve information from İzmir Ulaşım MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool's name and the context of sibling tools that clearly perform Read operations (searching routes, retrieving schedules, locating stations, calculating distances), hat_ara appears to be a query/search function for transportation data.
From the tool's definition Tool name 'hat_ara' (likely meaning 'search route' in Turkish) aligns with sibling tools on this server that perform queries like 'hat_detaylarini_ara' (search route details) and 'hattin_anlik_otobus_konumlarini_getir' (get real-time bus locations).
Attacks that exploit this kind of access
hat_ara. It is categorised as a Read tool in the İzmir Ulaşım MCP Server MCP Server, which means it retrieves data without modifying state.
Register the İzmir Ulaşım MCP Server MCP server in PolicyLayer and add a rule for hat_ara: 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 İzmir Ulaşım MCP Server. Nothing to install.
hat_ara 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 hat_ara 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 hat_ara. 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.
hat_ara is provided by the İzmir Ulaşım MCP Server MCP server (ogulcanakca/izmir-ulasim-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 →