Add multiple tasks or projects to OmniFocus in a single operation
AI agents use batch_add_items to create or update resources in Codex Omnifocus — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Codex Omnifocus environment.
This tool creates new tasks or projects in the user's OmniFocus database. While creation is reversible (tasks can be deleted), batch operations amplify the risk—a single agent call could create many unwanted items. The operation is Write rather than Execute because it doesn't run external code or scripts, and not Destructive because additions are reversible.
From the tool's definition Tool description states 'Add multiple tasks or projects to OmniFocus in a single operation'. The verb 'add' indicates creation of new data structures.
Attacks that exploit this kind of access
Add multiple tasks or projects to OmniFocus in a single operation. It is categorised as a Write tool in the Codex Omnifocus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Codex Omnifocus MCP server in PolicyLayer and add a rule for batch_add_items: 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 Codex Omnifocus. Nothing to install.
batch_add_items 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 batch_add_items 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 batch_add_items. 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.
batch_add_items is provided by the Codex Omnifocus MCP server (phd-peter/codex-omnifocus-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →