Cancel a running query.
AI agents invoke cancel_query to trigger actions in Imply Druid. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Cancelling a query triggers an external server-side operation (aborting an executing query). It is not purely read-only, nor does it delete data, but it does actively interrupt a running process. This falls under Execute as it triggers an external operation. Severity is medium because misuse could disrupt legitimate queries but has no data-loss or financial impact.
From the tool's definition Cancel a running query — terminates an in-progress operation on the server.
Attacks that exploit this kind of access
Cancel a running query. It is categorised as a Execute tool in the Imply Druid MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Imply Druid MCP server in PolicyLayer and add a rule for cancel_query: 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 Imply Druid. Nothing to install.
cancel_query is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the cancel_query 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 cancel_query. 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.
cancel_query is provided by the Imply Druid MCP server (yeongbin-hwang/imply-druid-mcp). 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 →