remove_dependency
AI agents call remove_dependency to permanently remove resources in Omniplan — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a dependency in a project plan is likely irreversible without manual re-creation. The sibling tool 'add_dependency' exists to create them, but no 'restore_dependency' exists, suggesting removal is a destructive action. Severity is medium as it affects project scheduling logic but not financial or system-level data. Confidence is reduced due to the empty description.
From the tool's definition Tool name 'remove_dependency' implies irreversible removal of a dependency relationship between tasks; description is empty and uninformative, lowering confidence.
Attacks that exploit this kind of access
remove_dependency. It is categorised as a Destructive tool in the Omniplan MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Omniplan MCP server in PolicyLayer and add a rule for remove_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.
remove_dependency is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_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 remove_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.
remove_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 →