check_users_risk
AI agents call check_users_risk to retrieve information from Oncallhealth without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to query or retrieve user risk information rather than modify, delete, or execute operations. It fits the 'Read' pattern of on-call health analysis tools that assess and report on burnout and workload status. With no destructive or side-effect capabilities evident, and no financial implications, this is classified as Read with low severity.
From the tool's definition Tool name 'check_users_risk' and context of sibling tools 'get_at_risk_users' and 'get_safe_responders' suggest this retrieves or queries risk status data. Description is empty, which lowers confidence slightly.
Attacks that exploit this kind of access
check_users_risk. It is categorised as a Read tool in the Oncallhealth MCP Server, which means it retrieves data without modifying state.
Register the Oncallhealth MCP server in PolicyLayer and add a rule for check_users_risk: 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 Oncallhealth. Nothing to install.
check_users_risk 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 check_users_risk 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 check_users_risk. 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.
check_users_risk is provided by the Oncallhealth MCP server (rootly-ai-labs/mcp-on-call-health). 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 →