AI agents use modify_health 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 modifies character game state but the changes are reversible—health can be restored, characters can be healed, and modifications can be undone or adjusted. It does not permanently delete data or irreversibly corrupt game state.
From the tool's definition Tool name 'modify_health' and description 'Modify a character' indicates reversible modification of game state data (character health attributes).
Documented attack patterns abuse exactly the kind of access modify_health 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 modify_health:
{
"version": "1",
"default": "deny",
"tools": {
"modify_health": {
"limits": [
{
"counter": "modify_health_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}modify_health 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.
Modify a character. 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 modify_health: 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.
modify_health 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 modify_health 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 modify_health. 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.
modify_health 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.