// SCAN REPORT

MCP OmniFocus

12 tools. 5 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 5 Jul 2026

5 can modify or destroy data

7 read-only

12 tools total

Community server · catalogue entry verified 05/07/2026

How to control MCP OmniFocus ↓

TOOL MAP

What MCP OmniFocus exposes to your agents

Read (7) Write / Execute (4) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous MCP OmniFocus tools

Destructive · High drop_task The 'drop_task' tool performs an irreversible deletion operation on task data in OmniFocus. Write · Medium activate_task This tool changes task metadata (completion/drop status) in a way that can be undone by calling complete_task or drop_task again. Write · Medium complete_task Completing a task is a reversible modification (tasks can be uncompleted in OmniFocus), so it falls under Write rather than Destructive. Write · Medium create_task Creating tasks is a reversible write operation—tasks can be modified or deleted later.

5 of MCP OmniFocus's 12 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCP OmniFocus

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP OmniFocus, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "drop_task": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "activate_task": {
    "limits": [
      {
        "counter": "activate_task_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "list_inbox": {
    "limits": [
      {
        "counter": "list_inbox_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register MCP OmniFocus — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP OMNIFOCUS →

Instant setup, no code required.

FULL CATALOGUE

All 12 MCP OmniFocus tools

DESTRUCTIVE 1 tools

Destructive drop_task Drop a task in OmniFocus.

WRITE 4 tools

Write activate_task Activate (un-drop or un-complete) a task in OmniFocus. Write complete_task Complete a task in OmniFocus. Write create_task create_task Write update_task update_task

READ 7 tools

Read list_inbox List all tasks in the OmniFocus Inbox. Read list_perspectives List all perspectives in OmniFocus. Read list_projects List all projects in OmniFocus. Read list_tasks List all tasks in OmniFocus. The task full name is the full heirarchy of the task, including parent tags. Read list_tasks_by_project list_tasks_by_project Read list_tasks_by_tag list_tasks_by_tag

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about MCP OmniFocus

Can an AI agent delete data through the MCP OmniFocus MCP server? +

Yes. The MCP OmniFocus server exposes 1 destructive tools including drop_task. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through MCP OmniFocus? +

The MCP OmniFocus server has 4 write tools including activate_task, complete_task, create_task. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach MCP OmniFocus.

How many tools does the MCP OmniFocus MCP server expose? +

12 tools across 3 categories: Destructive, Read, Write. 7 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on MCP OmniFocus? +

Register the MCP OmniFocus MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every MCP OmniFocus tool call.

Deterministic rules across all 12 MCP OmniFocus tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP OMNIFOCUS →

Instant setup, no code required.

12 MCP OmniFocus tools catalogued and risk-classified — across an index of 43,000+ MCP servers.