AI agents call check_duplicate 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 tool reads data from the freee system to detect duplicates before registration. It is a preventive check that queries existing records without creating, modifying, or deleting anything. The purpose is informational (preventing double-posting), making it a Read operation. Severity is low because misuse would at worst skip a duplicate check, not cause data loss or financial harm.
From the tool's definition The tool 'check_duplicate' performs a query operation: 'Check if a transaction already exists in freee (= by date + amount + memo prefix)'. It retrieves/searches data by matching transaction attributes and returns existence status with no side effects.
Attacks that exploit this kind of access
Check if a transaction already exists in freee (= by date + amount + memo prefix). Use BEFORE register to prevent double-posting. 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_duplicate: 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_duplicate 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_duplicate 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_duplicate. 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_duplicate 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 →