AI agents invoke start_timer to trigger actions in Harvest MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes a command that changes application state (starts timer tracking in Harvest). While not directly financial on its own, it operates within a financial context (time tracking for billing). It is not a simple read operation, nor is it destructive or write-oriented in the data modification sense.
From the tool's definition Tool description: 'Start a new timer.' This initiates an external operation (timer tracking) whose effects depend on context and timing arguments.
Documented attack patterns abuse exactly the kind of access start_timer 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 start_timer:
{
"version": "1",
"default": "deny",
"tools": {
"start_timer": {
"limits": [
{
"counter": "start_timer_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}start_timer stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Start a new timer. It is categorised as a Execute tool in the Harvest MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Harvest MCP Server MCP server in PolicyLayer and add a rule for start_timer: 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.
start_timer is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start_timer 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 start_timer. 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.
start_timer is provided by the Harvest MCP Server MCP server (taiste/harvest-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 Harvest MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
21 Harvest MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.