AI agents call get_tracker_stats to retrieve information from Jhabit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query operation that retrieves and returns computed statistics about a habit or quit tracker. There are no side effects, data modifications, destructive actions, or financial operations involved. The function signature and description clearly indicate it only fetches existing data.
From the tool's definition Tool description states 'Get stats for a tracker' which retrieves statistical data about existing trackers without modifying or deleting any data.
Attacks that exploit this kind of access
Get stats for a tracker: streaks for habits, abstinence time for quits. It is categorised as a Read tool in the Jhabit MCP Server, which means it retrieves data without modifying state.
Register the Jhabit MCP server in PolicyLayer and add a rule for get_tracker_stats: 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 Jhabit. Nothing to install.
get_tracker_stats 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_tracker_stats 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_tracker_stats. 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_tracker_stats is provided by the Jhabit MCP server (jacob-stokes/jhabit-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 →