Return HabitTracker summary stats for a daily metric type over N days.
AI agents call get_metric_summary to retrieve information from Poke HabitTracker MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns summary statistics about health metrics tracked over a time period. It is a read-only operation that retrieves historical data from HabitTracker without side effects. The severity is low because misuse would only expose personal health data to the AI agent, not cause irreversible damage or financial harm.
From the tool's definition Tool name 'get_metric_summary' and description 'Return HabitTracker summary stats for a daily metric type over N days' indicate retrieval of aggregated data with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Return HabitTracker summary stats for a daily metric type over N days. It is categorised as a Read tool in the Poke HabitTracker MCP MCP Server, which means it retrieves data without modifying state.
Register the Poke HabitTracker MCP server in PolicyLayer and add a rule for get_metric_summary: 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 Poke HabitTracker MCP. Nothing to install.
get_metric_summary 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_metric_summary 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_metric_summary. 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_metric_summary is provided by the Poke HabitTracker MCP server (smoothiekanoble/poke-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 →