AI agents call search_anayasa_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.
This tool searches a legal database (Turkish Constitutional Court decisions) and retrieves information. Search and retrieval operations have no side effects—they do not modify, execute code, delete data, or incur financial obligations. Even if search results inform legal decisions, the tool itself only reads.
From the tool's definition Tool name 'search_anayasa_unified' indicates a search operation. Sibling tools (get_* and fetch) are retrieval operations with no described write/delete/execute capabilities. 'Anayasa' refers to Turkish constitutional law documents.
Attacks that exploit this kind of access
search_anayasa_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_anayasa_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_anayasa_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_anayasa_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_anayasa_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_anayasa_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 →