# AWS Data Processing

AWS Data Processing connects coding assistants to AWS Glue, Amazon EMR, and Amazon Athena to manage data catalogs, coordinate ETL pipelines, and run SQL queries.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 9939 repo stars
- Author: awslabs
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/awslabs/mcp/tree/HEAD/src/aws-dataprocessing-mcp-server
- Updated: 2026-10-23
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/aws-data-processing

## What it does

The server gives coding assistants direct access to AWS Glue, Amazon EMR on EC2, and Amazon Athena. It handles data catalog operations, schema exploration, crawler scheduling, and interactive sessions for Spark or Ray workloads. Assistants can also inspect ETL jobs and coordinate visual workflows.

For heavy data processing, the integration configures EMR clusters with support for both on-demand and spot instance fleets. Inside Athena, the assistant submits SQL queries, checks runtime stats, manages workgroups, and explores federated data catalogs.

Your host system needs Python 3.10+, the `uv` tool, and AWS CLI credentials. Without attached IAM permissions for Glue, EMR, and Athena, every remote action will fail with access errors.

## Requirements
- Needs: Docker
- Works with: AWS

## Install

### Claude Code (native platform)

**Install**
- The MCP registry has no launch command for it: see the repository README

## When to use it
- inspect schemas and partitions across AWS Glue Data Catalog
- provision Amazon EMR clusters using on-demand or spot instances
- execute SQL queries in Amazon Athena and track their performance
- coordinate ETL workflows and interactive Spark or Ray sessions

## Example prompts
- Inspect tables in AWS Glue Data Catalog and display partition schemas
- Execute this SQL query in Amazon Athena and fetch the result rows
- Start a Spark interactive session in AWS Glue to test my ETL logic

## Similar
- [aws-data-analytics](https://affpapa.org/en/nevibecode/plugins/aws-data-analytics.md) — plugin · ★ 3536 repo stars
- [connecting-to-data-source](https://affpapa.org/en/nevibecode/skills/connecting-to-data-source.md) — skill · 7700 installs
- [aws-rds](https://affpapa.org/en/nevibecode/skills/aws-rds.md) — skill · 365 installs
- [aws-cloudformation-dynamodb](https://affpapa.org/en/nevibecode/skills/aws-cloudformation-dynamodb.md) — skill · ★ 372 repo stars
- [aws-cloudformation-rds](https://affpapa.org/en/nevibecode/skills/aws-cloudformation-rds.md) — skill · ★ 372 repo stars
- [iac-terraform-data-engineering](https://affpapa.org/en/nevibecode/skills/iac-terraform-data-engineering.md) — skill · 1800 installs

From the same set: [awslabs/mcp](https://affpapa.org/en/nevibecode/by/awslabs/mcp.md) — 36 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
