AWS MCP Servers
A collection of AWS-focused MCP servers for working with AWS services and cloud development workflows.
Start from the system you operate: a cloud account, a Kubernetes cluster, infrastructure configuration, or a delivery pipeline. Compare established cloud guides with new official servers and skills, then open the setup guide for your environment.
19 guides · 14 MCP / 5 Skills
These are actual directory guides grouped by operational task. An MCP connection supplies tools; a skill supplies workflow instructions. Review the individual guide for credentials, transport, and the operations it can expose.
| Your task | Start here | How to choose |
|---|---|---|
| Inspect an existing cloud account | Provider and platform servers | Choose the vendor you already use, then begin with inventory and logs before requesting changes. |
| Diagnose a Kubernetes workload | Google Kubernetes Engine MCP | Use cluster, event, and workload context together rather than guessing from an application error alone. |
| Plan infrastructure changes | Infrastructure and platform guidance | Use Terraform context or provider skills to prepare a plan; review live resource operations separately. |
| Investigate a delivery failure | Delivery and workflow operations | Start with pipeline or flow-run evidence, then follow the affected service into its provider guide. |
No matching guides. Try another search or reset the filters.
Choose the integration matching the account and platform you actually operate.
A collection of AWS-focused MCP servers for working with AWS services and cloud development workflows.
Connect assistants to Cloudflare services through Cloudflare’s MCP servers.
Connect an assistant to Cloud Run deployment and service-management workflows.
Manage DigitalOcean infrastructure through service-specific hosted MCP endpoints or the vendor’s local server.
Inspect GKE clusters, Kubernetes workloads, logs, and upgrade risks using Google Cloud’s MCP server.
Connect a coding assistant to Firebase projects, Authentication, Firestore, security rules, and other Firebase development tools.
Inspect and manage Heroku applications, dynos, add-ons, pipelines, logs, and PostgreSQL resources through MCP.
Inspect Render services, deployment events, logs, metrics, and Postgres resources from your AI client.
Connect infrastructure context with instructions for configuring and operating your platform.
Retrieve Terraform provider, module, and policy context for infrastructure workflows.
Connect MCP clients to Consul service discovery, health checks, key-value data, service mesh, and ACL operations.
Use HashiCorp’s MCP server to manage Vault mounts, key-value secrets, and PKI workflows.
Apply Cloudflare’s agent skills to development on the Cloudflare platform.
Use Microsoft’s Azure skills plugin to combine Azure workflow guidance with Azure MCP and Foundry MCP tools.
Add Firebase-specific instructions and resources to coding agents working on Firebase applications.
Follow build, container, deployment, and background-job context into the next diagnostic step.
Inspect Buildkite pipelines, builds, jobs, artifacts, and test information from an MCP client.
Search Docker Hub images and inspect repositories and tags with Docker’s own MCP integration.
Inspect Prefect flows, runs, deployments, logs, work pools, and automations using its experimental MCP server.
Install Railway’s use-railway skill and plugin integration, with hosted MCP access for Railway account workflows.
Build durable background tasks, AI chat agents, workflows, and realtime application interfaces with Trigger.dev’s own skills.
Use a server when the task needs connected resource context or tools. Use a skill when the assistant needs platform-specific instructions. Some plugins bundle both; each guide explains its installation path.
Reading a directory guide does not connect an account or run a tool. After installing a server yourself, its credentials and exposed tools determine the operations your client can request.
Follow the cloud provider guide for resource state and the observability collection for telemetry. Keep the same application, environment, and incident time window when moving between tools.
Explore the fourth batch: 29 official cloud, payment, security, and monitoring additions →
See all 25 additions in the third batch → · Full directory →