Best MCP servers for cloud infrastructure
Managing cloud infrastructure from an agent means letting it inspect and operate the resources that run your systems, compute, storage, networking, databases, and the edge, scoped safely so it can answer questions and make changes without you living in a console. The right server is the cloud you actually run on, and the leverage comes from an agent that can reason across services: check what is deployed, diagnose a misconfiguration, or stand up a resource through natural language. The servers below cover the major clouds and the edge platform many teams pair with them, each a real MCP server with a verified, current install config.
AWS (AWS Labs)
AWS Labs
Run any AWS CLI command from an agent, with validation, read-only mode, and command suggestions.
The AWS Labs server gives an agent access to AWS services and documentation, the pick for the most common cloud, so it can reason about and operate your AWS resources.
Google Cloud Run
Google Cloud
Google Cloud's official Cloud Run MCP server: deploy local code or file contents to Cloud Run, list and inspect services, and read service logs from your agent.
Google Cloud Run's server lets an agent deploy and manage services on GCP's serverless platform, ideal when your workloads run on Google Cloud.
Azure
Microsoft
Microsoft's official Azure MCP Server: manage 40+ Azure services — storage, Key Vault, Cosmos DB, SQL, Monitor, AKS, App Service, and more — from your agent.
Azure's server connects an agent to Azure resources and management operations, the natural fit for Microsoft-cloud shops.
Cloudflare
Cloudflare
Cloudflare's remote MCP servers: build and manage Workers, KV, R2, D1, and Hyperdrive from an agent.
Cloudflare's remote servers let an agent build and manage Workers, KV, R2, D1, and Hyperdrive, covering the edge and serverless layer that often fronts your cloud infrastructure.