AI agents use create_tasks to create or update resources in OmniFocus MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your OmniFocus MCP Server environment.
This tool creates new tasks in OmniFocus, which is a reversible data modification operation (tasks can be deleted via delete_tasks). It does not execute external code, trigger financial transactions, or permanently destroy data. Classification as Write is appropriate.
From the tool's definition Tool name 'create_tasks' indicates creation of new task items. Server description confirms the tool enables 'create' operations for 'tasks' and that users can 'create, update, and filter items'.
Documented attack patterns abuse exactly the kind of access create_tasks gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OmniFocus MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_tasks:
{
"version": "1",
"default": "deny",
"tools": {
"create_tasks": {
"limits": [
{
"counter": "create_tasks_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_tasks 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.
create_tasks. It is categorised as a Write tool in the OmniFocus MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the OmniFocus MCP Server MCP server in PolicyLayer and add a rule for create_tasks: 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 OmniFocus MCP Server. Nothing to install.
create_tasks 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 create_tasks 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 create_tasks. 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.
create_tasks is provided by the OmniFocus MCP Server MCP server (s-morgan-jeffries/omnifocus-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OmniFocus 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.
21 OmniFocus MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.