Push an update from an external agent into the game game. USE CASE: External agents (research agents, worldbuilders, lore generators, etc.) can push updates that the primary DM agent will receive and incorporate. EXAMPLES: - A research agent discovers detailed lore about a faction - A worldbuilde...
AI agents use push_external_update to create or update resources in DMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your DMCP environment.
This tool creates or modifies game data (lore, NPC backstories, plot elements, environmental details) within the game state. The changes are reversible and do not permanently destroy data or trigger irreversible external actions. While it modifies state, it lacks the destructive finality of delete operations and the external side-effects of Execute category tools.
From the tool's definition Tool description states it 'Push an update from an external agent into the game' and examples show creating/modifying game state: 'discovers detailed lore', 'generates NPC backstory', 'flags a plot hole', 'provides environmental details'.
Documented attack patterns abuse exactly the kind of access push_external_update 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 push_external_update:
{
"version": "1",
"default": "deny",
"tools": {
"push_external_update": {
"limits": [
{
"counter": "push_external_update_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}push_external_update stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Push an update from an external agent into the game game. USE CASE: External agents (research agents, worldbuilders, lore generators, etc.) can push updates that the primary DM agent will receive and incorporate. EXAMPLES: - A research agent discovers detailed lore about a faction - A worldbuilder generates NPC backstory - A consistency checker flags a plot hole - An atmosphere generator provides environmental details The DM agent should periodically check for pending updates via get_pending_updates. It is categorised as a Write tool in the DMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the D MCP server in PolicyLayer and add a rule for push_external_update: 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.
push_external_update is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the push_external_update 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 push_external_update. 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.
push_external_update 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.