Generate schema-aware query suggestions with ready-to-run SQL. Great for exploring unfamiliar databases or finding useful queries.
AI agents call suggest_queries to retrieve information from ThinAir Data without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool produces query suggestions and SQL text for the user to review, which is fundamentally a read/generative operation with no direct execution or data modification. The 'ready-to-run' phrasing introduces slight ambiguity about whether queries are automatically executed, but the description emphasizes suggestion and exploration rather than execution, keeping this in the Read category.
From the tool's definition "Generate schema-aware query suggestions with ready-to-run SQL" and "exploring unfamiliar databases or finding useful queries" — the tool generates/suggests SQL queries rather than executing them
Attacks that exploit this kind of access
Generate schema-aware query suggestions with ready-to-run SQL. Great for exploring unfamiliar databases or finding useful queries. It is categorised as a Read tool in the ThinAir Data MCP Server, which means it retrieves data without modifying state.
Register the ThinAir Data MCP server in PolicyLayer and add a rule for suggest_queries: 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 ThinAir Data. Nothing to install.
suggest_queries 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 suggest_queries 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 suggest_queries. 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.
suggest_queries is provided by the ThinAir Data MCP server (thinairtelematics/thinair-data). 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 →