Taking on 2–3 new engagements in 2026 — EST & PST hours

See how we work →
Cloud & Infra★ 9,434

awslabs/mcp

by awslabs · awslabs/mcp

How to use awslabs/mcp with Claude

awslabs/mcp is a Model Context Protocol (MCP) server that gives Claude and other AI agents direct access to cloud & infra capabilities. Once installed, you can use it in Claude Desktop, Cursor, VS Code with GitHub Copilot, or any MCP-compatible client.

MCP servers in the Cloud & Infra category let AI agents interact directly with cloud & infra systems — no custom API integration required. awslabs/mcp is built in Python. See the GitHub repository for full documentation and configuration options.

Setup

  1. Clone or install from the GitHub repository
  2. Follow the README for environment setup and credentials
  3. Add the server to your MCP client config (claude_desktop_config.json or .cursor/mcp.json)
  4. Restart your client — awslabs/mcp will appear in the available tools list

About awslabs/mcp

Python★ 9,434 starsUpdated Jul 2026Source: awesome

awslabs/mcp is an open-source MCP server in the Cloud & Infra category, built in Python. It connects Claude and other MCP-compatible clients to cloud & infra systems directly. Source available on GitHub.

Use cases for Cloud & Infra MCP servers

  • Query cloud resource state and metrics in real time
  • Automate infrastructure changes with AI-assisted validation
  • Debug deployment failures by pulling logs and config diffs
  • Monitor costs and trigger alerts on anomalies

Where awslabs/mcp fits in an MCP workflow

Teams use awslabs/mcp to give Claude a direct bridge into cloud & infra workflows, so routine actions happen inside the AI client instead of across separate tabs and dashboards.

awslabs/mcp can be connected to MCP clients by following the repository setup instructions, making it useful for teams that want AI access to cloud & infra systems.

More Cloud & Infra MCP servers

Built with MCP?

Altor deploys MCP servers into production for B2B engineering teams.

We connect AI agents to your live systems — ClickHouse, Linear, Stripe, GitHub — using MCP and deploy them to production in 3 weeks. Not demo.

Talk to Altor →