AI agents use move-media to create or update resources in Mcp Dev — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Dev environment.
Moving media items in a CMS changes metadata (parent location/hierarchy) and organizational state. This is a reversible modification action (Write category), not destructive. Severity is medium because misuse could disorganize media libraries or move sensitive media to accessible locations, but the action can be undone by moving items back. It does not delete, execute code, or trigger financial transactions.
From the tool's definition Tool performs 'Move a media item to a new location' - this modifies the state and structure of media assets within Umbraco CMS by relocating them, which is a reversible Write operation rather than deletion or destruction.
Attacks that exploit this kind of access
Move a media item to a new location. It is categorised as a Write tool in the Mcp Dev MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Dev MCP server in PolicyLayer and add a rule for move-media: 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 Mcp Dev. Nothing to install.
move-media 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-media 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-media. 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-media is provided by the Mcp Dev MCP server (@umbraco-cms/mcp-dev). 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 →