Alert check: compares last 7d vs prior 7d avg wellness for a drop.
AI agents call get_institution_alert_check to retrieve information from Wellness Pulse without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes historical wellness data by comparing two time periods to detect downward trends. It performs a statistical comparison operation (7-day vs prior 7-day average) to generate an alert signal, but does not modify any data, execute code, delete records, or trigger financial transactions.
From the tool's definition Tool name and description indicate data retrieval and comparison operations: 'Alert check: compares last 7d vs prior 7d avg wellness for a drop.' The verb 'compares' and the structure of querying wellness metrics suggest read-only analysis without…
Attacks that exploit this kind of access
Alert check: compares last 7d vs prior 7d avg wellness for a drop. It is categorised as a Read tool in the Wellness Pulse MCP Server, which means it retrieves data without modifying state.
Register the Wellness Pulse MCP server in PolicyLayer and add a rule for get_institution_alert_check: 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 Pulse. Nothing to install.
get_institution_alert_check 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 get_institution_alert_check 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 get_institution_alert_check. 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.
get_institution_alert_check is provided by the Wellness Pulse MCP server (prmail/wellness-pulse). 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 →