List active sessions + blocking locks. Uses the dialect
AI agents call show_locks 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 queries database metadata about active sessions and lock states. It has no side effects—it only retrieves diagnostic information about the current state of locks and sessions. The low severity reflects minimal blast radius; misuse would only expose information about system state, not execute commands or modify data.
From the tool's definition Tool name 'show_locks' and description 'List active sessions + blocking locks' indicates the tool retrieves and displays database lock information without modifying or executing operations. The verb 'list' and 'show' are characteristic of read operations.
Attacks that exploit this kind of access
List active sessions + blocking locks. Uses the dialect. 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 show_locks: 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.
show_locks 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 show_locks 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 show_locks. 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.
show_locks 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 →