# AWS MCP Server A Model Context Protocol (MCP) server that provides tools to interact with AWS services through Claude Desktop. ## Features -
If you already use AWS, the aws mcp server is the piece that lets your assistant work with it directly. # AWS MCP Server A Model Context Protocol (MCP) server that provides tools to interact with AWS services through Claude Desktop. ## Features - S3: List buckets, list objects - EC2: Describe instances, security groups, VPCs -.
aws-mcp-server on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
EC2 — Describe instances, security groups, VPCsRDS — Describe database instancesCloudWatch — Retrieve metric statisticsPrerequisites — The Prerequisites tool exposed by this serverInstallation — 1. Install the package: bash pip install aws-mcp-serverConfiguration is passed through the environment: AWS_MCP_PORT, AWS_MCP_DEBUG, ENABLE_VECTOR_STORE, YOUR_ACCESS_KEY, YOUR_SECRET_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
~/.aws/credentials) - Claude Desktop installedPlenty of cloud and infrastructure servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. AWS's toolset — EC2, RDS, CloudWatch and 2 more — is a fair guide to whether it matches your workflow. It is maintained by Havoc24k; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| EC2 | Describe instances, security groups, VPCs |
| RDS | Describe database instances |
| CloudWatch | Retrieve metric statistics |
| Prerequisites | The Prerequisites tool exposed by this server. |
| Installation | 1. **Install the package:** bash pip install aws-mcp-server |
{
"mcpServers": {
"aws-sa-tools": {
"command": "uvx",
"args": ["aws-mcp-server"],
"env": {
"AWS_MCP_PORT": "your-value",
"AWS_MCP_DEBUG": "your-value",
"ENABLE_VECTOR_STORE": "your-value",
"YOUR_ACCESS_KEY": "your-value",
"YOUR_SECRET_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
~/.aws/credentials) - Claude Desktop installed| Variable | Description | Required |
|---|---|---|
| AWS_MCP_PORT | Configuration value read at startup. | Optional |
| AWS_MCP_DEBUG | Configuration value read at startup. | Optional |
| ENABLE_VECTOR_STORE | Configuration value read at startup. | Optional |
| YOUR_ACCESS_KEY | Credential the server authenticates with. | Yes |
| YOUR_SECRET_KEY | Credential the server authenticates with. | Yes |
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
AWS Labs' official server suite — current AWS docs, CDK guidance, cost analysis and service tools.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.
Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.