AI agents use add_dependency to create or update resources in Omniplan — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Omniplan environment.
Adding a dependency between tasks modifies project structure but is reversible—it creates a relationship that can be undone by removing the dependency. This is a Write operation (structural modification), not Destructive, though confidence is moderate due to empty description.
From the tool's definition Tool name 'add_dependency' and server context indicate task/project relationship creation in OmniPlan 4. No description provided, but sibling tools (create_task, create_resource, delete_task, delete_resource) confirm this is a project management server where…
Attacks that exploit this kind of access
add_dependency. It is categorised as a Write tool in the Omniplan MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Omniplan MCP server in PolicyLayer and add a rule for add_dependency: 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 Omniplan. Nothing to install.
add_dependency 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_dependency 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_dependency. 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_dependency is provided by the Omniplan MCP server (johntrandall/omniplan-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 →