AI agents call search_direct_procurements to retrieve information from İhale MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a search operation on procurement data, returning results without modifying or executing anything. Search operations are Read category by definition. Severity is low because the data being searched (public procurement information) is non-sensitive and already publicly available through the EKAP v2 portal.
From the tool's definition Tool name 'search_direct_procurements' indicates a search operation. Sibling tools on the server are all Read operations (search_*, get_*). The server purpose is to 'search and access Turkish public procurement data'.
Attacks that exploit this kind of access
search_direct_procurements. It is categorised as a Read tool in the İhale MCP MCP Server, which means it retrieves data without modifying state.
Register the İhale MCP server in PolicyLayer and add a rule for search_direct_procurements: 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 İhale MCP. Nothing to install.
search_direct_procurements 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_direct_procurements 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_direct_procurements. 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_direct_procurements is provided by the İhale MCP server (saidsurucu/ihale-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 →