AI agents use create-dictionary 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.
Dictionary items in Umbraco are configuration/localization data that can be created and later removed. This is a reversible write operation with moderate blast radius—an agent could pollute the dictionary namespace or create unwanted entries, but the effects are not destructive or financial.
From the tool's definition Tool creates a new dictionary item in Umbraco CMS. 'Creates' is explicit Write language indicating data creation that is reversible (dictionary items can be deleted or modified afterward).
Attacks that exploit this kind of access
Creates a new dictionary item. 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 create-dictionary: 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.
create-dictionary 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 create-dictionary 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 create-dictionary. 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.
create-dictionary 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 →