AI agents call search_bedesten_unified to retrieve information from Yargı MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool operates within a legal database system (Yargı MCP) focused on retrieving court decisions and legal documents. The naming convention (search_*) and context of sibling retrieval tools suggests this performs queries against the Bedesten database (likely a Turkish legal/administrative decisions repository) without modification.
From the tool's definition Tool name 'search_bedesten_unified' indicates a search operation. The sibling tools (fetch, get_*_document_*) all appear to be Read operations that retrieve legal documents from Turkish government databases. The tool description is empty, limiting clarity.
Attacks that exploit this kind of access
search_bedesten_unified. It is categorised as a Read tool in the Yargı MCP MCP Server, which means it retrieves data without modifying state.
Register the Yargı MCP server in PolicyLayer and add a rule for search_bedesten_unified: 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 Yargı MCP. Nothing to install.
search_bedesten_unified 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_bedesten_unified 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_bedesten_unified. 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_bedesten_unified is provided by the Yargı MCP server (saidsurucu/yargi-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 →