start_wandering_combat
Atomically turn a module-authored pending wandering result into a strict-declaration combat against the loaded party. The printed/module count expression is rolled by the engine, the named compendium monster is validated, active durable party effects are restored, and the pending handoff is clear...
This record as markdown: /tools/torch-to-crown/start-wandering-combat.md
What start_wandering_combat does on Torch-to-Crown
AI agents invoke start_wandering_combat to trigger actions in Torch-to-Crown. 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 start_wandering_combat is rated High
start_wandering_combat triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
The rule that runs start_wandering_combat 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 start_wandering_combat, this is the rule to start with:
start_wandering_combat 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Torch-to-Crown, apply this rule, and every start_wandering_combat call is checked against it from then on.
Questions about start_wandering_combat
Atomically turn a module-authored pending wandering result into a strict-declaration combat against the loaded party. The printed/module count expression is rolled by the engine, the named compendium monster is validated, active durable party effects are restored, and the pending handoff is cleared only after combat was created successfully. It is categorised as a Execute tool in the Torch-to-Crown MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Torch-to-Crown MCP server in PolicyLayer and add a rule for start_wandering_combat: 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.
start_wandering_combat 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 start_wandering_combat 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 start_wandering_combat. 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.
start_wandering_combat 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.
Across the catalogue