bs_human_fire · Ttt MCP: Risk & Policy

WHAT IT DOES

What bs_human_fire does on Ttt

AI agents invoke bs_human_fire to trigger actions in Ttt. 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 bs_human_fire needs a policy

Although presented as a game tool, the function performs an Execute-class action: it triggers an operation (cannon fire) whose effects depend directly on the coordinates argument provided. This mirrors shell command or API call execution patterns. The high severity reflects that an AI agent could misuse coordinate arguments to cause unintended game state changes or actions.

From the tool's definition Tool name 'bs_human_fire' with description 'Fire the pirate cannons at the given coordinates on the Navy' indicates execution of an external action (firing cannons) based on provided arguments (coordinates).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

bs_human_fire Rate-limited

bs_human_fire 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": {
    "bs_human_fire": {
      "limits": [
        {
          "counter": "bs_human_fire_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 Ttt, so you can run agents against it safely.

FAQ

Questions about bs_human_fire

What does the bs_human_fire tool do? +

Fire the pirate cannons at the given coordinates on the Navy. It is categorised as a Execute tool in the Ttt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on bs_human_fire? +

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

What risk level is bs_human_fire? +

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

Can I rate-limit bs_human_fire? +

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

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

bs_human_fire is provided by the Ttt MCP server (srmtech-git/mcparcade). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.