AI agents use add-subtask to create or update resources in KanbanFlow MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your KanbanFlow MCP Server environment.
The tool creates new subtask records within a task management system. This is a Write operation because it adds/creates data reversibly. Severity is low because subtasks are non-critical task metadata with minimal blast radius—an erroneous subtask can be easily removed or ignored.
From the tool's definition Tool name 'add-subtask' and description 'Add a subtask to an existing task' indicate creation of new data (a subtask) within an existing task structure. This is a reversible modification operation.
Documented attack patterns abuse exactly the kind of access add-subtask gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and KanbanFlow MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for add-subtask:
{
"version": "1",
"default": "deny",
"tools": {
"add-subtask": {
"limits": [
{
"counter": "add-subtask_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add-subtask 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.
Add a subtask to an existing task. It is categorised as a Write tool in the KanbanFlow MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the KanbanFlow MCP Server MCP server in PolicyLayer and add a rule for add-subtask: 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 KanbanFlow MCP Server. Nothing to install.
add-subtask 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 add-subtask 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 add-subtask. 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.
add-subtask is provided by the KanbanFlow MCP Server MCP server (williamavholmberg/kanbanflow-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from KanbanFlow 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.
16 KanbanFlow MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.