surprise_check
Roll 1d6 per side at the start of an encounter; a side is surprised on a 1–2.
This record as markdown: /tools/torch-to-crown/surprise-check.md
What surprise_check does on Torch-to-Crown
AI agents call surprise_check to retrieve information from Torch-to-Crown without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why surprise_check is rated Low
Even though surprise_check only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs surprise_check safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Torch-to-Crown, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For surprise_check, this is the rule to start with:
surprise_check is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Torch-to-Crown, apply this rule, and every surprise_check call is checked against it from then on.
Questions about surprise_check
Roll 1d6 per side at the start of an encounter; a side is surprised on a 1–2. It is categorised as a Read tool in the Torch-to-Crown MCP Server, which means it retrieves data without modifying state.
Register the Torch-to-Crown MCP server in PolicyLayer and add a rule for surprise_check: 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 Torch-to-Crown. Nothing to install.
surprise_check is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the surprise_check 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 surprise_check. 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.
surprise_check is provided by the Torch-to-Crown MCP server (Diogenes187/Torch-to-Crown). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Torch-to-Crown, and thousands of servers like it.
This server
Across the catalogue