Low Risk

filter_tasks

Advanced task filtering with unlimited perspective combinations - status, dates, projects, tags, search, and more

How to control filter_tasks ↓

What filter_tasks does on OmniFocus MCP Enhanced

AI agents call filter_tasks to retrieve information from OmniFocus MCP Enhanced without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why filter_tasks needs a policy

This tool retrieves and displays filtered subsets of task data based on multiple criteria (status, dates, projects, tags, search). The description emphasizes filtering and perspective combinations, which are read-only operations. No language indicates creation, modification, deletion, or execution of external operations.

From the tool's definition Tool name 'filter_tasks' and description 'Advanced task filtering with unlimited perspective combinations - status, dates, projects, tags, search, and more' indicate a querying/retrieval operation that applies filters to existing tasks without modification or…

Documented attack patterns abuse exactly the kind of access filter_tasks gives an agent:

How to control filter_tasks

PolicyLayer is an MCP gateway — it sits between your AI agents and OmniFocus MCP Enhanced, and nothing reaches the server without passing your rules. This is the rule we recommend for filter_tasks:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "filter_tasks": {}
  }
}

filter_tasks is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register OmniFocus MCP Enhanced — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about filter_tasks

What does the filter_tasks tool do? +

Advanced task filtering with unlimited perspective combinations - status, dates, projects, tags, search, and more. It is categorised as a Read tool in the OmniFocus MCP Enhanced MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on filter_tasks? +

Register the OmniFocus MCP Enhanced MCP server in PolicyLayer and add a rule for filter_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 Enhanced. Nothing to install.

What risk level is filter_tasks? +

filter_tasks is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit filter_tasks? +

Yes. Add a rate_limit block to the filter_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.

How do I block filter_tasks completely? +

Set action: deny in the PolicyLayer policy for filter_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.

What MCP server provides filter_tasks? +

filter_tasks is provided by the OmniFocus MCP Enhanced MCP server (jqlts1/omnifocus-mcp-enhanced). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every OmniFocus MCP Enhanced tool call.

Start from OmniFocus MCP Enhanced, 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.

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

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.