AI agents use create_tracker to create or update resources in Jhabit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Jhabit environment.
This tool creates new data structures (habit/quit trackers) but does not execute arbitrary code, delete data irreversibly, move money, or read sensitive information without modification. Creation of application data is a Write operation. Severity is low because misuse would simply result in extra tracker records that can be managed or deleted, with no cascading damage or financial impact.
From the tool's definition Tool name 'create_tracker' and description 'Create a new habit or quit tracker' indicate data creation that is reversible (trackers can be deleted via the sibling 'delete_entry' tool).
Attacks that exploit this kind of access
Create a new habit or quit tracker. It is categorised as a Write tool in the Jhabit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Jhabit MCP server in PolicyLayer and add a rule for create_tracker: 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.
create_tracker is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_tracker 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 create_tracker. 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.
create_tracker 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 →