Compute utilization metrics for a date range. Shows how much of available capacity is being used, with billable vs non-billable breakdown. Can group by user, client, project, task, date, week, or month.
AI agents call harvest_compute_utilization to retrieve information from Harvest MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and aggregates time-tracking data to produce utilization reports. No data is created, modified, or deleted; no external code is executed; no financial transactions occur. It is purely informational analysis of existing Harvest data, making it a Read operation with low risk.
From the tool's definition Tool description states 'Compute utilization metrics' and 'Shows how much of available capacity is being used' — these are read-only analytics operations that retrieve and analyze existing data without modifying, deleting, or executing external operations.
Documented attack patterns abuse exactly the kind of access harvest_compute_utilization gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Harvest MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for harvest_compute_utilization:
{
"version": "1",
"default": "deny",
"tools": {
"harvest_compute_utilization": {}
}
}harvest_compute_utilization is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Compute utilization metrics for a date range. Shows how much of available capacity is being used, with billable vs non-billable breakdown. Can group by user, client, project, task, date, week, or month. It is categorised as a Read tool in the Harvest MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Harvest MCP Server MCP server in PolicyLayer and add a rule for harvest_compute_utilization: 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 Harvest MCP Server. Nothing to install.
harvest_compute_utilization 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 harvest_compute_utilization 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 harvest_compute_utilization. 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.
harvest_compute_utilization is provided by the Harvest MCP Server MCP server (southleft/harvest-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Harvest MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
21 Harvest MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.