AI agents use mark_subtask_done to create or update resources in TaskFlow MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your TaskFlow MCP environment.
An AI agent can call mark_subtask_done faster than any human can review — one bad instruction and it creates or modifies resources in TaskFlow MCP by the hundred, each call as confident as the last.
Documented attack patterns abuse exactly the kind of access mark_subtask_done gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and TaskFlow MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for mark_subtask_done:
{
"version": "1",
"default": "deny",
"tools": {
"mark_subtask_done": {
"limits": [
{
"counter": "mark_subtask_done_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}mark_subtask_done 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.
Mark a subtask as done. Provide. It is categorised as a Write tool in the TaskFlow MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the TaskFlow MCP server in PolicyLayer and add a rule for mark_subtask_done: 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 TaskFlow MCP. Nothing to install.
mark_subtask_done 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 mark_subtask_done 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 mark_subtask_done. 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.
mark_subtask_done is provided by the TaskFlow MCP server (pinkpixel-dev/taskflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 23 TaskFlow MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
23 TaskFlow MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.