Fix actual start/end timestamps for a task. Used to correct timestamps for historical accuracy. Past dates allowed. Args: task_id: ID of the task to fix actual_start: New actual start in ISO format (e.g., '2025-12-13T09:00:00') actual_end: New actual end in ISO format (e.g., '2025-12-13T17:00:00'...
AI agents use fix_actual_times to create or update resources in Taskdog — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Taskdog environment.
This tool modifies existing task data (timestamps and duration fields) in a reversible way — it overwrites time metadata but the original values could be restored by another call. It does not execute code, delete records, or involve financial operations. The blast radius is medium since incorrect timestamps could corrupt audit trails or time-tracking records, but the effect is limited to metadata on a single task.
From the tool's definition Fix actual start/end timestamps for a task. Used to correct timestamps for historical accuracy.
Documented attack patterns abuse exactly the kind of access fix_actual_times gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Taskdog, and nothing reaches the server without passing your rules. This is the rule we recommend for fix_actual_times:
{
"version": "1",
"default": "deny",
"tools": {
"fix_actual_times": {
"limits": [
{
"counter": "fix_actual_times_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}fix_actual_times 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.
Fix actual start/end timestamps for a task. Used to correct timestamps for historical accuracy. Past dates allowed. Args: task_id: ID of the task to fix actual_start: New actual start in ISO format (e.g., '2025-12-13T09:00:00') actual_end: New actual end in ISO format (e.g., '2025-12-13T17:00:00') actual_duration: Explicit duration in hours (e.g., 0.5 = 30min, 1.5 = 1h30m) clear_start: Clear actual_start timestamp clear_end: Clear actual_end timestamp clear_duration: Clear actual_duration (use calculated value) Returns: Updated task data with new timestamps. It is categorised as a Write tool in the Taskdog MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Taskdog MCP server in PolicyLayer and add a rule for fix_actual_times: 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 Taskdog. Nothing to install.
fix_actual_times 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 fix_actual_times 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 fix_actual_times. 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.
fix_actual_times is provided by the Taskdog MCP server (kohei-wada/taskdog). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Taskdog, 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.
26 Taskdog tools catalogued and risk-classified — across an index of 43,000+ MCP servers.