AI agents invoke ksef_test_connection_check to trigger actions in KSeF MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool performs an authentication action against an external system (KSeF TEST environment) and persists state ('persist readiness'), which constitutes triggering an external operation with side effects. It is not a pure read — it writes/persists session or readiness state. It does not create invoices directly, but it executes an auth flow and stores results, placing it in Execute rather than Write or Read.
From the tool's definition Authenticate to KSeF TEST and persist readiness before invoice XML generation
Attacks that exploit this kind of access
Authenticate to KSeF TEST and persist readiness before invoice XML generation. It is categorised as a Execute tool in the KSeF MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the KSeF MCP server in PolicyLayer and add a rule for ksef_test_connection_check: 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_test_connection_check is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ksef_test_connection_check 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_test_connection_check. 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_test_connection_check 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 →