# AWS IoT SiteWise

Hooks your coding agent up to AWS IoT SiteWise: industrial assets, models, telemetry, gateways and S3 metadata transfers.

- 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-iot-sitewise-mcp-server
- Updated: 2026-10-23
- Security check: automated, 2026-11-16 (text) — warning: a command downloads a script from astral.sh and runs it right away. Do not run such commands without an explicit yes from the human.
- HTML: https://affpapa.org/en/nevibecode/mcp/aws-iot-sitewise

## What it does

The server exposes SiteWise through MCP tools. Build and edit assets, wire up hierarchies, define asset models with measurements, attributes, transforms and metrics. On the data side it reads time series over a chosen window, works out averages, sums, counts, min/max and standard deviation, and fills gaps by interpolation.

Migration runs through metadata transfer jobs that move resources between S3 and SiteWise, with schema checks before an import and progress tracking while the job works. Anomaly detection and computation models train, get versions and serve inference. Edge gateways, access policies and KMS encryption are covered too, and two prompts ship along: one walks the asset tree, one steps through ingestion setup.

Python 3.10 or newer and AWS credentials are the entry price. Those credentials need SiteWise access (full, if you plan to write), IoT TwinMaker for transfers and S3 for bulk jobs. Without them the process starts and tool calls fail. Point your MCP client at `uvx` with `awslabs.aws-iot-sitewise-mcp-server@latest` and set `AWS_REGION`.

## 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
- create an industrial asset and attach it to a model
- pull a sensor's history for a given time range
- compute min/max and average for a property
- export every asset model to S3 in one job
- configure an Edge gateway for a protocol

## Example prompts
- Show the asset hierarchy for the plant floor with current property values.
- Create an asset model with a temperature measurement and an hourly average metric.
- Export all assets and models to the S3 bucket with a metadata transfer job.

## Similar
- [timestream-influxdb](https://affpapa.org/en/nevibecode/skills/timestream-influxdb.md) — skill · 5100 installs
- [aws-database](https://affpapa.org/en/nevibecode/skills/aws-database.md) — skill · 6700 installs
- [aws-rds-spring-boot-integration](https://affpapa.org/en/nevibecode/skills/aws-rds-spring-boot-integration.md) — skill · 3900 installs
- [aws-dynamodb](https://affpapa.org/en/nevibecode/skills/aws-dynamodb.md) — skill · 530 installs
- [aws-rds](https://affpapa.org/en/nevibecode/skills/aws-rds.md) — skill · 365 installs
- [aws-aurora](https://affpapa.org/en/nevibecode/skills/aws-aurora.md) — skill · 288 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
