AI agents call get-dictionary-by-id-array to retrieve information from Mcp Dev without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves dictionary items from Umbraco CMS based on provided IDs. It performs a simple query operation that reads data without creating, modifying, deleting, or executing any operations. The return of an empty array when no IDs are provided further confirms it is a safe read-only operation with no destructive or side-effect capabilities.
From the tool's definition Tool name contains 'get-' prefix and description states 'Gets dictionary items by IDs', indicating data retrieval with no side effects.
Attacks that exploit this kind of access
Gets dictionary items by IDs (or empty array if no IDs are provided). It is categorised as a Read tool in the Mcp Dev MCP Server, which means it retrieves data without modifying state.
Register the Mcp Dev MCP server in PolicyLayer and add a rule for get-dictionary-by-id-array: 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.
get-dictionary-by-id-array is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get-dictionary-by-id-array 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 get-dictionary-by-id-array. 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.
get-dictionary-by-id-array 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 →