AI agents use move_resource 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.
The tool appears to create or modify resource state (moving/reassigning) within a project management context, making it a Write operation. It is reversible (resources can be moved again), so not Destructive. Severity is medium because misuse could disrupt project structure, but the impact is limited to resource allocation without financial consequences.
From the tool's definition Tool name 'move_resource' suggests relocating or reassigning a resource within OmniPlan 4. Given the sibling tools include 'assign_resource' and 'create_resource', this likely modifies resource allocation or positioning rather than deleting it.
Attacks that exploit this kind of access
move_resource. 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 move_resource: 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.
move_resource 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 move_resource 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 move_resource. 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.
move_resource 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 →