Return recent queries executed through ThinAir with timing, row counts, and status. [BUILD tier]
AI agents call query_history 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.
This tool returns audit/history logs of past query execution. It retrieves existing data about queries that were previously run, their performance metrics, and outcomes. There is no data creation, modification, deletion, code execution, or financial impact.
From the tool's definition Tool description states 'Return recent queries executed through ThinAir' — retrieves historical metadata (timing, row counts, status) without modifying or executing operations. No side effects; purely informational query.
Attacks that exploit this kind of access
Return recent queries executed through ThinAir with timing, row counts, and status. [BUILD tier]. 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 query_history: 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.
query_history 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 query_history 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 query_history. 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.
query_history 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 →