Track time spent on tasks and projects.
AI agents use pilotgentic_time_tracker to create or update resources in PilotGentic — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PilotGentic environment.
This tool creates and modifies time-tracking data (recording task durations, project allocations, etc.), making it a Write operation. It doesn't execute external commands or delete data (not Execute or Destructive), and has no financial impact (not Financial).
From the tool's definition Tool description states 'Track time spent on tasks and projects', indicating creation and modification of time-tracking records. The verb 'track' implies recording and storing temporal data about task activities.
Attacks that exploit this kind of access
Track time spent on tasks and projects. It is categorised as a Write tool in the PilotGentic MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the PilotGentic MCP server in PolicyLayer and add a rule for pilotgentic_time_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 PilotGentic. Nothing to install.
pilotgentic_time_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 pilotgentic_time_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 pilotgentic_time_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.
pilotgentic_time_tracker is provided by the PilotGentic MCP server (@pilotgentic/mcp-server). 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 →