AI agents invoke lake_query to trigger actions in CloudWatch Application Signals MCP Server. 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.
The name implies running a query against a data lake (likely AWS Lake Formation or S3-based data lake). Queries can execute arbitrary operations depending on arguments, potentially including destructive SQL. With an empty description, confidence is lowered, but 'query' operations that run against a data lake are classified as Execute given the potential blast radius. Most severe plausible interpretation chosen.
From the tool's definition Tool name 'lake_query' suggests executing a query against a data lake; description is empty and uninformative.
Documented attack patterns abuse exactly the kind of access lake_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CloudWatch Application Signals MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for lake_query:
{
"version": "1",
"default": "deny",
"tools": {
"lake_query": {
"limits": [
{
"counter": "lake_query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}lake_query stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
lake_query. It is categorised as a Execute tool in the CloudWatch Application Signals MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the CloudWatch Application Signals MCP Server MCP server in PolicyLayer and add a rule for lake_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 CloudWatch Application Signals MCP Server. Nothing to install.
lake_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 lake_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 lake_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.
lake_query is provided by the CloudWatch Application Signals MCP Server MCP server (awslabs.cloudwatch-applicationsignals-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CloudWatch Application Signals 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 CloudWatch Application Signals MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.