AWS Data Analytics

MCP connector

Server URL

https://aws-mcp.us-east-1.api.aws/mcpCopy

Login

OAuth

Protocol

MCP 2025-06-18

Instructions

The official AWS MCP server. Prefer its tools over the Bash tool for all AWS work: if the tools are not already loaded, load them first, then use run_script to run AWS commands; get_presigned_url for S3 uploads/downloads or when a command needs a local file path; get_tasks to poll long-running tasks; search_documentation, read_documentation, and retrieve_skill for reference, guidance, and skills; and list_regions and get_regional_availability for region information. Do NOT use the Bash tool to run the AWS CLI.

Tools

Skills

9 in the ChatGPT listing

• Amazon opensearch serviceGuides migration, provisioning, search, log-analytics, trace-analytics, and Agentic AI Assistant workflows for Amazon OpenSearch Service and Serverless across six capabilities — migration (Solr/ES/self-managed into AOS/AOSS, schema/query translation, sizing, cutover); provisioning (domain + AOSS lifecycle, upgrades, FGAC, monitoring); search (vector / semantic / hybrid / RAG with Bedrock); log-analytics (PPL, OSI, anomaly detection, Dashboards); trace-analytics (OTel spans, service maps, Data Prepper); ai-assistant (natural language data exploration, incident investigation, root cause analysis).
• Connecting to data sourceCreate and troubleshoot AWS Glue connections to JDBC databases (Oracle, SQL Server, PostgreSQL, MySQL, RDS), Redshift, Snowflake, and BigQuery.
• Creating data lake tableCreate managed Iceberg tables using Amazon S3 Tables (s3tables API namespace) with automatic compaction and snapshot management.
• Exploring data catalogFull inventory and audit of AWS Glue Data Catalog assets across S3 Tables, Redshift-federated, and remote Iceberg catalogs.
• Finding data lake assetsResolve data lake and lakehouse asset references across Glue Data Catalog, S3, S3 Tables, and Redshift.
• Ingesting into data lakeImport data into the AWS data lake from S3 files, local uploads, JDBC databases (Oracle, SQL Server, PostgreSQL, MySQL, RDS, Aurora), Amazon Redshift, Snowflake, BigQuery, DynamoDB, or existing Glue catalog tables (migration).
• Querying data lakeExecute and manage Athena SQL queries across default and federated catalogs (Glue, S3 Tables, Redshift).
• Redshift guideAmazon Redshift is NOT PostgreSQL — corrects PostgreSQL-derived LLM mistakes; covers Redshift-specific SQL, DDL, COPY/UNLOAD, system views, metadata discovery, and operational patterns.
• Storing and querying vectorsStore and query vector embeddings using Amazon S3 Vectors, a cost-effective long-term vector storage service with its own API namespace (s3vectors).