AI agents use move-dictionary-item 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 a dictionary item is a write operation that modifies the organizational structure of CMS content. While reversible, it can have significant impact on content hierarchy and potentially affect content delivery or multilingual string mappings in Umbraco. Severity is 'high' because misuse could disrupt site content organization and translations across multiple languages.
From the tool's definition Tool performs 'Moves a dictionary item' operation - modifies the location/structure of an existing dictionary item within Umbraco CMS. The term 'move' indicates a reversible structural modification rather than deletion or creation.
Attacks that exploit this kind of access
Moves a dictionary item by Id. 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-dictionary-item: 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-dictionary-item 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-dictionary-item 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-dictionary-item. 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-dictionary-item 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 →