AI agents call evaluate_records_acl to retrieve information from Kintone MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes access control information for records. It does not create, modify, delete, or execute operations—it only assesses permissions based on conditions. The blast radius of misuse is minimal; an attacker could gain visibility into access policies but cannot alter them or affect data integrity. This is characteristic of a Read category tool.
From the tool's definition Tool name 'evaluate_records_acl' and description 'evaluates access permissions for records under specified conditions' indicate a query/assessment operation.
Documented attack patterns abuse exactly the kind of access evaluate_records_acl gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kintone MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for evaluate_records_acl:
{
"version": "1",
"default": "deny",
"tools": {
"evaluate_records_acl": {}
}
}evaluate_records_acl is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
指定した条件でレコードのアクセス権限を評価します. It is categorised as a Read tool in the Kintone MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Kintone MCP Server MCP server in PolicyLayer and add a rule for evaluate_records_acl: 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 Kintone MCP Server. Nothing to install.
evaluate_records_acl 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 evaluate_records_acl 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 evaluate_records_acl. 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.
evaluate_records_acl is provided by the Kintone MCP Server MCP server (r3-yamauchi/kintone-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kintone MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
70 Kintone MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.