Fire the Navy cannons at the given coordinates on the pirate fleet. Claude chooses the target — reason about it in chat first, then call this. Returns hit/miss/sunk — and if sunk, reveals what the pirate ship was carrying.
AI agents invoke bs_claude_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.
This is an Execute tool because it runs an action (firing cannons) that has state-changing effects in the battleship game. It's not Read (no mere query), not Write (not creating/modifying data reversibly — game state changes are asymmetric), not Destructive (data deletion doesn't apply), not Financial.
From the tool's definition Tool description states 'Fire the Navy cannons at the given coordinates' and 'Claude chooses the target' — this triggers an external operation (cannon fire action) whose effects depend on the argument (coordinates chosen by Claude).
Attacks that exploit this kind of access
Fire the Navy cannons at the given coordinates on the pirate fleet. Claude chooses the target — reason about it in chat first, then call this. Returns hit/miss/sunk — and if sunk, reveals what the pirate ship was carrying. 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.
Register the Ttt MCP server in PolicyLayer and add a rule for bs_claude_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.
bs_claude_fire is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the bs_claude_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.
Set action: deny in the PolicyLayer policy for bs_claude_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.
bs_claude_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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →