AI agents call evaluate_item_data_quality to retrieve information from Sana without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name indicates data evaluation/quality checking, which is typically a read-only inspection operation with no side effects. However, the empty description creates ambiguity about whether this tool performs validation only or triggers corrective actions.
From the tool's definition Tool name 'evaluate_item_data_quality' suggests an assessment/inspection function that examines item data without modifying it. No description provided; confidence reduced accordingly.
Attacks that exploit this kind of access
evaluate_item_data_quality. It is categorised as a Read tool in the Sana MCP Server, which means it retrieves data without modifying state.
Register the Sana MCP server in PolicyLayer and add a rule for evaluate_item_data_quality: 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 Sana. Nothing to install.
evaluate_item_data_quality 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 evaluate_item_data_quality 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 evaluate_item_data_quality. 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.
evaluate_item_data_quality is provided by the Sana MCP server (sana-mcp-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 →