AI agents use save_workhour to create or update resources in Workhour — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Workhour environment.
The tool saves/writes timesheet data to persistent storage. While the empty description limits certainty, the name and server context indicate data modification rather than read-only access. Categorized as Write (not Destructive) because timesheets are typically reversible—they can be corrected or amended.
From the tool's definition Tool name 'save_workhour' indicates it persists timesheet data. Server description mentions 'file them' (timesheets) and 'two-step confirmation', suggesting write operations with safeguards.
Attacks that exploit this kind of access
save_workhour. It is categorised as a Write tool in the Workhour MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Workhour MCP server in PolicyLayer and add a rule for save_workhour: 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 Workhour. Nothing to install.
save_workhour 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 save_workhour 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 save_workhour. 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.
save_workhour is provided by the Workhour MCP server (Calvin-Ca/workhour-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
save_workhour is one line of Workhour's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →