AI agents use draw_cards to create or update resources in MCP Rand — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Rand environment.
An AI agent can call draw_cards faster than any human can review — one bad instruction and it creates or modifies resources in MCP Rand by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Draw cards from a standard deck of playing cards. It is categorised as a Write tool in the MCP Rand MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Rand MCP server in PolicyLayer and add a rule for draw_cards: 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 MCP Rand. Nothing to install.
draw_cards 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 draw_cards 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 draw_cards. 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.
draw_cards is provided by the MCP Rand MCP server (turlockmike/mcp-rand). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.