This repository provides an implementation of a Model Context Protocol (MCP) server for AWS S3, enabling AI models, particularly Large Language
This repository provides an implementation of a Model Context Protocol (MCP) server for AWS S3, enabling AI models, particularly Large Language Models (LLMs), to
To use this server, developers need: - Python 3.10 or higher - Configured AWS credentials (Access Key ID, Secret Access Key, and Region) - uv package manager (recommended) or pip - Familiarity with the Model Context Protocol for AI application integration
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"server-s3-download-files": {
"command": "uvx",
"args": ["mcp-s3-server"],
"env": {
"AWS_ACCESS_KEY_ID": "your-value",
"AWS_SECRET_ACCESS_KEY": "your-value",
"AWS_DEFAULT_REGION": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
To use this server, developers need: - Python 3.10 or higher - Configured AWS credentials (Access Key ID, Secret Access Key, and Region) - uv package manager (recommended) or pip - Familiarity with the Model Context Protocol for AI application integration
| Variable | Description | Required |
|---|---|---|
| AWS_ACCESS_KEY_ID | Credential the server authenticates with. | Yes |
| AWS_SECRET_ACCESS_KEY | Credential the server authenticates with. | Yes |
| AWS_DEFAULT_REGION | Configuration value read at startup. | Optional |
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.
kubectl with a conversational interface — inspect pods, read logs, diagnose clusters and manage workloads.