gemini_command · LINE Bot MCP Server MCP: Risk & Policy

WHAT IT DOES

What gemini_command does on LINE Bot MCP Server

AI agents invoke gemini_command to trigger actions in LINE Bot MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why gemini_command needs a policy

While the tool itself is a planning/wrapper around LINE messaging operations, it qualifies as Execute because it: (1) runs code/AI logic to determine which LINE action to perform, (2) can trigger message broadcasts to users (a side effect dependent on AI reasoning), and (3) could be misused to spam or impersonate communications.

From the tool's definition Tool executes 'one LINE action' via Gemini, including state-changing operations like 'push/broadcast text or flex' messages to LINE users. The description explicitly mentions executing actions that send messages to users.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gemini_command Rate-limited

gemini_command stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "gemini_command": {
      "limits": [
        {
          "counter": "gemini_command_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about gemini_command

What does the gemini_command tool do? +

Use Gemini to plan and execute one LINE action (get profile, get rich menu list, get message quota, push/broadcast text or flex). It is categorised as a Execute tool in the LINE Bot MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on gemini_command? +

Register the LINE Bot MCP Server MCP server in PolicyLayer and add a rule for gemini_command: 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 LINE Bot MCP Server. Nothing to install.

What risk level is gemini_command? +

gemini_command is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit gemini_command? +

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

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

gemini_command is provided by the LINE Bot MCP Server MCP server (tndfame/mcp_management). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.