hesapla_ceza
AI agents call hesapla_ceza to retrieve information from mimari-ai MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to calculate or look up penalty amounts from regulatory data, which is a read operation. Without a description, confidence is reduced. The context of a regulatory/standards server suggests informational retrieval rather than side effects.
From the tool's definition Tool name 'hesapla_ceza' translates to 'calculate penalty/fine'. No description provided. Based on sibling tools that perform calculations (hesapla_maliyet=calculate cost, hesapla_otopark=calculate parking, hesapla_taks=calculate tax) and query/search…
Attacks that exploit this kind of access
hesapla_ceza. It is categorised as a Read tool in the mimari-ai MCP Server MCP Server, which means it retrieves data without modifying state.
Register the mimari-ai MCP Server MCP server in PolicyLayer and add a rule for hesapla_ceza: 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 mimari-ai MCP Server. Nothing to install.
hesapla_ceza 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 hesapla_ceza 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 hesapla_ceza. 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.
hesapla_ceza is provided by the mimari-ai MCP Server MCP server (uzungridera/mimari-ai-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 →