AI agents call validate_sql_only to retrieve information from Xugu without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool checks SQL correctness without executing it, meaning it cannot read, write, delete, or modify any data. It is purely an analysis/validation operation. The 'Read' category encompasses information retrieval tools, and validation—while not fetching data—is a safe introspection operation. Severity is low because misuse cannot cause data loss, modification, or financial impact.
From the tool's definition Tool performs validation only: 'Validate SQL query without LLM explanation (lightweight mode)'. The name contains 'validate' and description explicitly states 'without' execution.
Attacks that exploit this kind of access
Validate SQL query without LLM explanation (lightweight mode). It is categorised as a Read tool in the Xugu MCP Server, which means it retrieves data without modifying state.
Register the Xugu MCP server in PolicyLayer and add a rule for validate_sql_only: 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 Xugu. Nothing to install.
validate_sql_only 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 validate_sql_only 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 validate_sql_only. 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.
validate_sql_only is provided by the Xugu MCP server (leokupo/xugu-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
validate_sql_only is one line of Xugu's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →