Get a single record from a Kintone app by record ID. ⚠️ Use
AI agents call kintone_get_record to retrieve information from Mcp Kintone Lite without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple read operation—fetching a single record by ID from a Kintone application. It does not create, modify, delete, or execute code. The blast radius of misuse is minimal; an attacker could access data they shouldn't see, but cannot modify or destroy it. Classified as Read with low severity.
From the tool's definition Tool name 'kintone_get_record' and description 'Get a single record from a Kintone app by record ID' indicate data retrieval with no modification or deletion. This is a query operation that retrieves existing data without side effects.
Attacks that exploit this kind of access
Get a single record from a Kintone app by record ID. ⚠️ Use. It is categorised as a Read tool in the Mcp Kintone Lite MCP Server, which means it retrieves data without modifying state.
Register the Mcp Kintone Lite MCP server in PolicyLayer and add a rule for kintone_get_record: 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 Mcp Kintone Lite. Nothing to install.
kintone_get_record 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 kintone_get_record 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 kintone_get_record. 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.
kintone_get_record is provided by the Mcp Kintone Lite MCP server (luvl/mcp-kintone-lite). 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 →