AI agents call search_bddk_decisions 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.
This tool retrieves publicly available Turkish banking regulatory decisions from a legal database. It performs informational lookups (search operations) with no side effects, no code execution, and no data modification. The blast radius of misuse is minimal—an LLM agent could retrieve irrelevant or excessive records, but cannot alter regulations, approve licenses, or affect financial systems.
From the tool's definition Tool name 'search_bddk_decisions' and description 'searching Turkish banking regulation (BDDK) decisions' indicate query/retrieval operations without modification or execution of external systems.
Attacks that exploit this kind of access
Use this when searching Turkish banking regulation (BDDK) decisions. For banking licenses, fintech, and payment services. 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_bddk_decisions: 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_bddk_decisions 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_bddk_decisions 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_bddk_decisions. 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_bddk_decisions 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 →