Prepare to pause the game. Returns a checklist of context to save and current game state. WHEN TO CALL: Before ending a game or when the player says they need to stop. This tool returns: - Current game state summary - Checklist of ephemeral context that should be saved - Any existing pause state ...
AI agents call prepare_pause to retrieve information from DMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and returns current game state information along with a checklist. It does not modify, delete, or execute anything — it is explicitly a preparatory read step before a separate 'save_pause_state' tool performs any writes.
From the tool's definition Prepare to pause the game. Returns a checklist of context to save and current game state.
Documented attack patterns abuse exactly the kind of access prepare_pause gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and DMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for prepare_pause:
{
"version": "1",
"default": "deny",
"tools": {
"prepare_pause": {}
}
}prepare_pause is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Prepare to pause the game. Returns a checklist of context to save and current game state. WHEN TO CALL: Before ending a game or when the player says they need to stop. This tool returns: - Current game state summary - Checklist of ephemeral context that should be saved - Any existing pause state - Instructions for what to save After calling this, use save_pause_state to persist your context. It is categorised as a Read tool in the DMCP MCP Server, which means it retrieves data without modifying state.
Register the D MCP server in PolicyLayer and add a rule for prepare_pause: 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 DMCP. Nothing to install.
prepare_pause 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 prepare_pause 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 prepare_pause. 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.
prepare_pause is provided by the D MCP server (shawnrushefsky/dmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from DMCP, 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.
204 DMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.