Add a new project to OmniFocus
AI agents use add_project 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 a new project in OmniFocus, which is a write operation that modifies the database by adding a new entity. It is reversible (the project can be deleted), so it falls under Write rather than Destructive. The severity is medium because while project creation itself is low-risk, an agent creating many unwanted projects could clutter the user's system, but the impact is recoverable.
From the tool's definition Tool name is 'add_project' and description states 'Add a new project to OmniFocus', which creates new data in the user's task management system.
Attacks that exploit this kind of access
Add a new project to OmniFocus. 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 add_project: 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.
add_project 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 add_project 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 add_project. 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.
add_project 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 →