AI agents call get-media-by-id-referenced-by 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 information about references to a media item. It performs a read-only query operation that returns existing data without creating, modifying, deleting, or executing any actions. The 'get' verb and passive language ('find', 'reference') confirm this is a data retrieval operation with minimal blast radius.
From the tool's definition Tool description states 'Get items that reference a specific media item' and 'find all content, documents, or other items that are currently referencing' - these are query/retrieval operations with no modification or side effects.
Attacks that exploit this kind of access
Get items that reference a specific media item Use this to find all content, documents, or other items that are currently referencing a specific media item. 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-media-by-id-referenced-by: 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-media-by-id-referenced-by 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-media-by-id-referenced-by 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-media-by-id-referenced-by. 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-media-by-id-referenced-by 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 →