AI agents call ksef_lookup_counterparty 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 public or semi-public Polish business registries to fetch counterparty information. It has no side effects, cannot modify data, and poses minimal risk if an AI agent calls it with arbitrary counterparty identifiers—it will simply return lookup results or failures. The 'advisory' framing confirms it is informational only.
From the tool's definition Tool description states 'Look up advisory counterparty data' — a retrieval operation with no modification or destructive intent. The verb 'look up' and qualifier 'advisory' indicate read-only querying of external registers (MF, VIES, KRS, GUS).
Attacks that exploit this kind of access
Look up advisory counterparty data from MF, VIES, KRS, or GUS sources. 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_counterparty: 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_counterparty 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_counterparty 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_counterparty. 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_counterparty 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 →