AI agents use update_app_customize to create or update resources in Kintone MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kintone MCP Server environment.
This tool modifies app configurations by updating JavaScript and CSS customizations. While it creates/updates configuration data rather than deleting it (which would be Destructive), injecting arbitrary JavaScript/CSS into a live application is a powerful Write operation with potentially significant blast radius—malicious code could access user data, manipulate UI behavior, exfiltrate information, or degrade app…
From the tool's definition Tool name 'update_app_customize' and description 'kintoneアプリのJavaScript/CSSカスタマイズ設定を更新します' (updates a Kintone app's JavaScript/CSS customization settings) indicates modification of application configuration through code injection.
Documented attack patterns abuse exactly the kind of access update_app_customize 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 update_app_customize:
{
"version": "1",
"default": "deny",
"tools": {
"update_app_customize": {
"limits": [
{
"counter": "update_app_customize_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_app_customize stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
kintoneアプリのJavaScript/CSSカスタマイズ設定を更新します. It is categorised as a Write tool in the Kintone MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kintone MCP Server MCP server in PolicyLayer and add a rule for update_app_customize: 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.
update_app_customize is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_app_customize 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 update_app_customize. 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.
update_app_customize 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.