AI agents use stop_timer to create or update resources in Harvest MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Harvest MCP Server environment.
Stopping a timer modifies the state of an active time entry (changes it from running to stopped). This is a reversible write operation — the timer can be restarted. It has no destructive, financial, or code-execution implications. Blast radius is low as it only affects a single active timer session.
From the tool's definition Stop a running timer
Documented attack patterns abuse exactly the kind of access stop_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 stop_timer:
{
"version": "1",
"default": "deny",
"tools": {
"stop_timer": {
"limits": [
{
"counter": "stop_timer_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}stop_timer stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Stop a running timer. It is categorised as a Write tool in the Harvest MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Harvest MCP Server MCP server in PolicyLayer and add a rule for stop_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.
stop_timer 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 stop_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 stop_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.
stop_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.