AI agents call getResourceReference to retrieve information from My without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get' prefix and 'Reference' noun suggest this tool retrieves or queries resource metadata without modifying state. Given the empty description, we cannot confirm side effects, but the naming convention aligns with Read operations. The low confidence reflects uncertainty due to missing documentation; if this tool actually executes queries or modifies resources, severity could be higher.
From the tool's definition Tool name 'getResourceReference' suggests a retrieval operation (get), and the lack of destructive action keywords implies read-only behavior. However, the description is empty, which limits confidence in the classification.
Attacks that exploit this kind of access
getResourceReference. It is categorised as a Read tool in the My MCP Server, which means it retrieves data without modifying state.
Register the My MCP server in PolicyLayer and add a rule for getResourceReference: 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 My. Nothing to install.
getResourceReference 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 getResourceReference 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 getResourceReference. 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.
getResourceReference is provided by the My MCP server (kcbabo/everything-server). 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 →