AI agents call ksef_lookup_exchange_rate to retrieve information from KSeF MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries external (Polish NBP) exchange-rate reference data. It has no side effects—it neither modifies data, executes arbitrary operations, triggers financial transactions, nor deletes anything. The 'advisory' nature and 'basis confirmation' requirement confirm it is informational. No AI misuse scenario results in data loss, code execution, or financial harm from this tool alone.
From the tool's definition Tool name includes 'lookup' and description states 'Fetch official NBP exchange-rate data'; both indicate retrieval of existing data with no modification, deletion, or execution of operations.
Attacks that exploit this kind of access
Fetch official NBP exchange-rate data; advisory and requires basis confirmation. It is categorised as a Read tool in the KSeF MCP MCP Server, which means it retrieves data without modifying state.
Register the KSeF MCP server in PolicyLayer and add a rule for ksef_lookup_exchange_rate: 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 KSeF MCP. Nothing to install.
ksef_lookup_exchange_rate 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 ksef_lookup_exchange_rate 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 ksef_lookup_exchange_rate. 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.
ksef_lookup_exchange_rate is provided by the KSeF MCP server (olegtyshcneko/ksef-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 →