Efficiently query OmniFocus database with powerful filters. Get specific tasks, projects, or folders without loading the entire database. Supports filtering by project, tags, status, due dates, and more. Much faster than dump_database for targeted queries.
AI agents call query_omnifocus to retrieve information from OmniFocus-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters data from the OmniFocus database without modifying, deleting, or executing operations. It is explicitly contrasted with dump_database as a more targeted query mechanism. The worst-case misuse would be unauthorized information disclosure of task/project data, which is a read-level risk with low severity in a personal productivity context.
From the tool's definition Tool description states: 'query OmniFocus database with powerful filters. Get specific tasks, projects, or folders without loading the entire database.' The verb 'query' and 'Get' indicate read-only retrieval.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access query_omnifocus gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OmniFocus-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for query_omnifocus:
{
"version": "1",
"default": "deny",
"tools": {
"query_omnifocus": {}
}
}query_omnifocus is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Efficiently query OmniFocus database with powerful filters. Get specific tasks, projects, or folders without loading the entire database. Supports filtering by project, tags, status, due dates, and more. Much faster than dump_database for targeted queries. It is categorised as a Read tool in the OmniFocus-MCP MCP Server, which means it retrieves data without modifying state.
Register the OmniFocus- MCP server in PolicyLayer and add a rule for query_omnifocus: 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. Nothing to install.
query_omnifocus is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the query_omnifocus 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 query_omnifocus. 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.
query_omnifocus is provided by the OmniFocus- MCP server (themotionmachine/omnifocus-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 12 OmniFocus-MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
12 OmniFocus-MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.