Pull a SURPRISE wellness item — the server picks a random uplifting format
AI agents call surprise_me to retrieve information from Wellness Manager without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the server's business model involving micropayments ($0.01 per item in USDC), this particular tool merely reads/retrieves a random wellness item. It has no side effects on data, does not execute code or commands, and does not move money directly—those financial mechanics are handled at the server infrastructure level, not by this tool's invocation.
From the tool's definition Tool name 'surprise_me' and description 'Pull a SURPRISE wellness item — the server picks a random uplifting format' indicate the tool retrieves data (a random wellness item) without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Pull a SURPRISE wellness item — the server picks a random uplifting format. It is categorised as a Read tool in the Wellness Manager MCP Server, which means it retrieves data without modifying state.
Register the Wellness Manager MCP server in PolicyLayer and add a rule for surprise_me: 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 Wellness Manager. Nothing to install.
surprise_me 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 surprise_me 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 surprise_me. 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.
surprise_me is provided by the Wellness Manager MCP server (wellnessagent/wellness-master). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →