Конвертирует сумму из одной валюты в другую
AI agents call convert_currency to retrieve information from Currency MCP Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Currency conversion here is a read/calculation operation: it computes the converted value using exchange rate data. The server description says it's a 'local service for currency rates and conversion,' implying it returns informational results rather than executing real financial transactions. No money is moved, no obligations are created.
From the tool's definition "Конвертирует сумму из одной валюты в другую" (Converts an amount from one currency to another) — this is a calculation/query operation using exchange rates, not an actual financial transaction
Attacks that exploit this kind of access
Конвертирует сумму из одной валюты в другую. It is categorised as a Read tool in the Currency MCP Agent MCP Server, which means it retrieves data without modifying state.
Register the Currency MCP Agent MCP server in PolicyLayer and add a rule for convert_currency: 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 Currency MCP Agent. Nothing to install.
convert_currency 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 convert_currency 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 convert_currency. 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.
convert_currency is provided by the Currency MCP Agent MCP server (mariakasimceva0305-ux/currency-mcp-agent). 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 →