send_push_message · LineWhiz MCP: Risk & Policy

WHAT IT DOES

What send_push_message does on LineWhiz

AI agents use send_push_message to create or update resources in LineWhiz — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LineWhiz environment.

WHY IT NEEDS A POLICY

Why send_push_message needs a policy

This tool sends messages to end users, which is a reversible write operation (messages can be deleted/recalled in some systems, and represent data creation/modification rather than irreversible deletion or execution of arbitrary code). While it could be misused to spam or harass users if an agent has access to many user IDs, the primary capability is message transmission—a Write action.

From the tool's definition Tool name 'send_push_message' and description 'Send a direct text message to a specific user by their LINE user ID' indicate the tool creates and transmits a message, which modifies the state of user communications.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_push_message Rate-limited

send_push_message 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": {
    "send_push_message": {
      "limits": [
        {
          "counter": "send_push_message_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 LineWhiz, so you can run agents against it safely.

FAQ

Questions about send_push_message

What does the send_push_message tool do? +

Send a direct text message to a specific user by their LINE user ID. It is categorised as a Write tool in the LineWhiz MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_push_message? +

Register the LineWhiz MCP server in PolicyLayer and add a rule for send_push_message: 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 LineWhiz. Nothing to install.

What risk level is send_push_message? +

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

Can I rate-limit send_push_message? +

Yes. Add a rate_limit block to the send_push_message 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 send_push_message completely? +

Set action: deny in the PolicyLayer policy for send_push_message. 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 send_push_message? +

send_push_message is provided by the LineWhiz MCP server (kinzen-dev/linewhiz). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.