AI agents call search_okas_codes 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.
This tool retrieves or queries classification code data from a procurement database with no apparent side effects. It fits the Read category pattern of the server (search, lookup operations). Severity is low because it only accesses reference/classification data. Confidence is reduced from 0.9 to 0.7 due to the empty tool description, which prevents direct confirmation of its exact behavior.
From the tool's definition Tool name 'search_okas_codes' indicates a search operation for classification codes (OKAS is a Turkish procurement classification system).
Attacks that exploit this kind of access
search_okas_codes. 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_okas_codes: 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_okas_codes 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_okas_codes 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_okas_codes. 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_okas_codes 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 →