Get the number of active visitors on a website during the last 5 minutes.
AI agents call umami_get_active to retrieve information from Umami MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries visitor metrics from Umami analytics without creating, modifying, deleting, or executing any operations. It is purely informational retrieval. Read category tools carry low severity because they do not alter systems or expose sensitive operations that could cause harm if misused by an AI agent.
From the tool's definition Server described as 'Read-only MCP server for Umami analytics' and tool 'umami_get_active' retrieves the 'number of active visitors' — a query operation with no side effects or data modification.
Attacks that exploit this kind of access
Get the number of active visitors on a website during the last 5 minutes. It is categorised as a Read tool in the Umami MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Umami MCP Server MCP server in PolicyLayer and add a rule for umami_get_active: 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 Umami MCP Server. Nothing to install.
umami_get_active 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 umami_get_active 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 umami_get_active. 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.
umami_get_active is provided by the Umami MCP Server MCP server (mzaxd/umami-mcp). 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 →