AWS publishes a reference architecture for a data lake MCP server: Fargate in private subnets, SELECT-only Athena tools, and one JSON metadata file to onboard a dataset
How to build an agent-agnostic gateway to a data lake: authentication, read-only limits, audit logs and the measured end-to-end latency.
// Key points
- Requests pass Route 53, a public load balancer with AWS WAF and Amazon Cognito authentication before reaching the MCP server on Fargate in private subnets, which is not reachable from the internet
- Three tool groups: SQL through Athena and Redshift, semantic search over docs and table metadata in Bedrock Knowledge Bases, and search over operational policies
- Athena tools allow only SELECT and reject writes; every tool call is logged to CloudWatch as structured JSON; session state lives in DynamoDB so Fargate tasks stay stateless
- Onboarding a dataset takes one JSON metadata file and no custom code; the lake holds thousands of datasets, and end-to-end latency in testing was 15 to 20 seconds
Builder's takeSELECT-only SQL plus a JSON log for every call is the minimum bar for giving agents data access, and worth copying as is. If we open AI Cloud Drive's storage dashboard to agent queries I would build it this way, but 15 to 20 seconds of latency fits analytical Q&A, not paths where a user is waiting.
// Background · from #AI agents
Full timeline →- Nov 9 Google measures agent distraction: 13% of sessions meet bug-referencing TODOs, and detoured sessions take 70% more steps and 77% more tokens
- Nov 9 Greenlight builds Luna, a security operations agent on AgentCore: up to 4,000 cases a month, more than 90% resolved without human intervention
- Nov 9 Okta Cross App Access on AgentCore, part 2: all traffic through one Gateway, Cedar policies in default-deny, and denied calls never redeem a token