lock_door · Seam MCP Server MCP: Risk & Policy

WHAT IT DOES

What lock_door does on Seam MCP Server

AI agents invoke lock_door to trigger actions in Seam 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 lock_door needs a policy

This tool sends a command that causes a real-world physical action: locking a door. It is not a simple data read or write, but an execution of an external operation with immediate physical consequences. Misuse could trap people inside or outside a space, making severity high. It is reversible (door can be unlocked), so it does not qualify as Destructive, but the physical safety implications elevate severity.

From the tool's definition 'Lock a specific door' — triggers a physical external operation (engaging a door lock mechanism via the Seam API)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

lock_door Rate-limited

lock_door 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": {
    "lock_door": {
      "limits": [
        {
          "counter": "lock_door_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 Seam MCP Server, so you can run agents against it safely.

FAQ

Questions about lock_door

What does the lock_door tool do? +

Lock a specific door. It is categorised as a Execute tool in the Seam 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 lock_door? +

Register the Seam MCP Server MCP server in PolicyLayer and add a rule for lock_door: 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 Seam MCP Server. Nothing to install.

What risk level is lock_door? +

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

Can I rate-limit lock_door? +

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

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

lock_door is provided by the Seam MCP Server MCP server (keithah/seam-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.