AI agents invoke start_combat to trigger actions in D&D 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.
This tool executes a combat encounter, which is an external operation that initiates game logic and state changes. While not directly destructive (no permanent data deletion) or financial, it performs an irreversible game action that changes campaign state and triggers complex combat mechanics.
From the tool's definition Tool name 'start_combat' and description 'Start a combat encounter' indicate triggering of a game state transition and combat mechanics execution whose effects depend on the encounter parameters and character states involved.
Documented attack patterns abuse exactly the kind of access start_combat gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and D&D MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for start_combat:
{
"version": "1",
"default": "deny",
"tools": {
"start_combat": {
"limits": [
{
"counter": "start_combat_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}start_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.
Free to start. No card required.
Start a combat encounter. It is categorised as a Execute tool in the D&D MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the D&D MCP Server MCP server in PolicyLayer and add a rule for start_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 D&D MCP Server. Nothing to install.
start_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_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_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_combat is provided by the D&D MCP Server MCP server (study-flamingo/gamemaster-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from D&D MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
30 D&D MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.