Monitor a table
AI agents call watch_table 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.
Monitoring a table is a read-only operation that observes data but does not create, modify, delete, or execute operations. It retrieves status information about table changes. No side effects, no irreversible actions, and no code execution are implied. This falls clearly into the Read category with low severity as the blast radius of misuse is minimal—an agent could only observe table activity, not alter it.
From the tool's definition Tool name 'watch_table' and description 'Monitor a table' indicate passive observation/retrieval of table state changes without modification, deletion, or code execution.
Attacks that exploit this kind of access
Monitor a table. 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 watch_table: 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.
watch_table 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 watch_table 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 watch_table. 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.
watch_table 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 →