Critical Risk →

cancel_logs_insight_query

cancel_logs_insight_query

How to control cancel_logs_insight_query ↓

What cancel_logs_insight_query does on AWS Step Functions Tool MCP Server

AI agents call cancel_logs_insight_query to permanently remove resources in AWS Step Functions Tool MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

Why cancel_logs_insight_query needs a policy

The name suggests cancelling a running CloudWatch Logs Insights query, which is an irreversible action (the query run is terminated and cannot be resumed). However, the description is empty, lowering confidence. Cancelling a query is relatively low blast radius since it only stops a read operation, but it is categorized as Destructive because the cancellation itself cannot be undone.

From the tool's definition Tool name: 'cancel_logs_insight_query' — 'cancel' implies terminating/stopping an in-progress operation

Documented attack patterns abuse exactly the kind of access cancel_logs_insight_query gives an agent:

How to control cancel_logs_insight_query

PolicyLayer is an MCP gateway — it sits between your AI agents and AWS Step Functions Tool MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for cancel_logs_insight_query:

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "cancel_logs_insight_query"
  ]
}

cancel_logs_insight_query disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

  1. Create a free account and register AWS Step Functions Tool MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RESTRICT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about cancel_logs_insight_query

What does the cancel_logs_insight_query tool do? +

cancel_logs_insight_query. It is categorised as a Destructive tool in the AWS Step Functions Tool MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on cancel_logs_insight_query? +

Register the AWS Step Functions Tool MCP Server MCP server in PolicyLayer and add a rule for cancel_logs_insight_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 AWS Step Functions Tool MCP Server. Nothing to install.

What risk level is cancel_logs_insight_query? +

cancel_logs_insight_query is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit cancel_logs_insight_query? +

Yes. Add a rate_limit block to the cancel_logs_insight_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.

How do I block cancel_logs_insight_query completely? +

Set action: deny in the PolicyLayer policy for cancel_logs_insight_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.

What MCP server provides cancel_logs_insight_query? +

cancel_logs_insight_query is provided by the AWS Step Functions Tool MCP Server MCP server (awslabs.stepfunctions-tool-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every AWS Step Functions Tool MCP Server tool call.

Start from AWS Step Functions Tool MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

805 AWS Step Functions Tool MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.