update_record · kintone MCP Server (Python3) MCP

WHAT IT DOES

What update_record does on kintone MCP Server (Python3)

AI agents use update_record to create or update resources in kintone MCP Server (Python3) — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your kintone MCP Server (Python3) environment.

WHY IT NEEDS A POLICY

Why update_record needs a policy

This tool modifies data reversibly by updating a single record. While update operations can have business impact depending on what fields are modified, they do not permanently delete data and can be undone through subsequent updates. The medium severity reflects that unauthorized updates could corrupt or compromise data integrity, but the impact is scoped to individual records and reversible.

From the tool's definition Tool name 'update_record' and description 'Update a single record in a kintone app' clearly indicate modification of existing data. The operation is reversible (data can be updated again to previous values), distinguishing it from destructive operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_record Rate-limited

update_record 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "update_record": {
      "limits": [
        {
          "counter": "update_record_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches kintone MCP Server (Python3), so you can run agents against it safely.

FAQ

Questions about update_record

What does the update_record tool do? +

Update a single record in a kintone app. It is categorised as a Write tool in the kintone MCP Server (Python3) MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on update_record? +

Register the kintone MCP Server (Python3) MCP server in PolicyLayer and add a rule for update_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 kintone MCP Server (Python3). Nothing to install.

What risk level is update_record? +

update_record is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit update_record? +

Yes. Add a rate_limit block to the update_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.

How do I block update_record completely? +

Set action: deny in the PolicyLayer policy for update_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.

What MCP server provides update_record? +

update_record is provided by the kintone MCP Server (Python3) MCP server (r3-yamauchi/kintone-mcp-server-python3). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.