AI agents invoke rcon to trigger actions in Minecraft Docker MCP. 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.
RCON (Remote CONsole) is a protocol that allows execution of arbitrary server console commands on a Minecraft server. This can include destructive operations (deleting builds, killing players, wiping worlds), administrative actions (op/deop players, whitelist changes), and general server management.
From the tool's definition Tool name 'rcon' on a server described as using 'RCON' to 'programmatically create Minecraft builds and manage the server'
Documented attack patterns abuse exactly the kind of access rcon gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Minecraft Docker MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for rcon:
{
"version": "1",
"default": "deny",
"tools": {
"rcon": {
"limits": [
{
"counter": "rcon_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}rcon 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.
rcon. It is categorised as a Execute tool in the Minecraft Docker MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Minecraft Docker MCP server in PolicyLayer and add a rule for rcon: 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 Minecraft Docker MCP. Nothing to install.
rcon 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 rcon 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 rcon. 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.
rcon is provided by the Minecraft Docker MCP server (rgbkrk/rcon-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Minecraft Docker MCP, 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.
6 Minecraft Docker MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.