AI agents call check_exclusion to retrieve information from Cockpit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only query tool that evaluates transactions against 7 Japanese accounting rules and reports the result. It has no side effects, does not modify data, and does not execute external operations. The low severity reflects minimal blast radius—misuse would only result in incorrect read/query responses, not data corruption or financial impact.
From the tool's definition check_exclusion returns a boolean determination (excluded:true/false) indicating whether a transaction should NOT be auto-journalized.
Attacks that exploit this kind of access
7-rule exclusion check for Japanese accounting. Returns excluded:true if transaction should NOT be auto-journalized. Rules: 内容不明デビット / 借入金返済 / 社保税金 / 給与支払い / 投資 / ATM出金 / 公共料金. It is categorised as a Read tool in the Cockpit MCP Server, which means it retrieves data without modifying state.
Register the Cockpit MCP server in PolicyLayer and add a rule for check_exclusion: 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 Cockpit. Nothing to install.
check_exclusion 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 check_exclusion 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 check_exclusion. 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.
check_exclusion is provided by the Cockpit MCP server (michielinksee/kansei-link-cockpit). 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 →