Pre-ingestion scanning for RAG documents
AI agents call scan_document to retrieve information from ZugaShield without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and inspects document content for security threats (consistent with ZugaShield's purpose) but produces no side effects—it does not create, modify, delete, or execute anything. It is purely an analytical/diagnostic read operation. Confidence is high because the functionality is clearly limited to inspection/scanning before data ingestion, which is a non-destructive read activity.
From the tool's definition Tool name 'scan_document' and description 'Pre-ingestion scanning for RAG documents' indicate the tool analyzes/inspects documents before they enter a RAG system.
Attacks that exploit this kind of access
Pre-ingestion scanning for RAG documents. It is categorised as a Read tool in the ZugaShield MCP Server, which means it retrieves data without modifying state.
Register the ZugaShield MCP server in PolicyLayer and add a rule for scan_document: 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 ZugaShield. Nothing to install.
scan_document 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 scan_document 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 scan_document. 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.
scan_document is provided by the ZugaShield MCP server (zuga-technologies/zugashield). 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 →