MCP For Claude Marketplace
Porter PaaS

Porter PaaS MCP Connector for Claude

A+

Orchestrate Kubernetes clusters via Porter — manage apps, projects, container tags, and enforce rollouts directly with your AI.

10 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect your Porter account to any AI agent and take full programmatic control over your Kubernetes infrastructure natively.

What you can do

  • Projects & Clusters — List high-level organizational bounds, EKS/GKE clusters, and deployment zones
  • Applications & Environments — Map staging/production namespaces, check active web services, and resolve container requirements
  • Operations — Restart app pods gracefully or forcefully deploy specific image tags when resolving CI/CD breaks
  • Helm Inspections — Check low-level Helm charts behind active components (like Postgres or Redis)

How it works

  1. Subscribe to this server
  2. Enter your Porter API Token
  3. Start managing your clusters straight from Claude, Cursor, or any MCP client

No pulling KUBECONFIG files, authenticating via cloud CLI tools, or navigating dashboards. Your orchestration lives in chat.

Who is this for?

  • DevOps Engineers — quickly restart crashing services and audit cluster architectures on the fly
  • Backend Developers — rollback image tags and orchestrate quick deployments directly from standard chat
  • Engineering Leads — inspect resource mapping and isolate distinct staging environments instantly
kubernetespaascontainer-orchestrationdeployment-automationcluster-managementinfrastructure-as-code

10 tools expose this connector's capabilities to your AI agent.

deploy_app_tag

Assigns a raw docker registry digest/tag directly causing Kubernetes to perform an absolute image pull orchestrating a fresh deployment state spanning replica boundaries. Forcefully mutate the executed Docker image running internally

get_app

Includes explicit CPU metrics requested, RAM limits mapped locally to the JVM/Node instances, and internal registry image hashes resolving at runtime. Analyze architectural bindings orchestrating a specific App

get_cluster

Inspect deep cloud credentials generating a specific K8s Cluster

get_project

Perform structural extraction of metadata linked to a Porter Project

list_apps

Discovers precisely which App routing identities expose `porter.run` subdomains or linked target custom apex mappings. Inventory deployed discrete Applications mapping to a Cluster

list_clusters

Exposes crucial execution zones hosting absolute memory nodes. List underlying target cloud Kubernetes definitions bounds to Porter

list_environments

Extract logic isolation environments overlapping the Cluster

list_projects

Fetches indispensable integer `projectId` arrays coordinating everything strictly downstream inside AWS/GCP clusters. Identify base Porter PaaS organizational scopes

list_helm_releases

Vital for verifying if dependent third-party apps (e.g. Postgres databases or Metabase) deployed aside the primary stack succeeded during installation phases. List underlying operational Helm configurations inside a namespace

restart_app

Mandatory during severe connection leakage scenarios impacting native processes without modifying the fundamental code layer deployment tag. Instruct the Kubernetes API to bounce the App deployment replicas

See how to talk to your AI agent using Porter PaaS.

List all applications currently running in cluster ID 5 on the Production environment.

I found 4 applications bound to the cluster namespace. We have `core-api`, `cron-sync-worker`, `redis-cache`, and `web-frontend`. The core API is serving on a porter.run subdomain mapping. Would you like me to get architectural configs for `core-api`?

The queue worker is completely hung. Please perform a forceful restart of the `async-worker` app.

Command received. I've sent the signal to recycle the pod replicas for `async-worker` across cluster 4. Kubernetes is now performing a rolling flush seamlessly. It will take roughly 15 seconds to stand out new instances and attach them.

We just built a hotfix on main. Deploy the image tag `d83a1b1` strictly onto `portal-frontend`.

I've successfully forced the container mutation! The `portal-frontend` application was patched to image tag `d83a1b1`. The cloud runner is pulling the fresh digest and orchestrating a replacement. Check the frontend in 1 minute.

Yes. If a specific commit tag needs to be rolled out bypassing regular CI delays, simply command the AI to `deploy_app_tag` providing the target container suffix. It issues direct orchestration commands triggering an absolute image update inside Kubernetes immediately.

Related Connectors

RE

RescueTime MCP

54 tools Official

Track productivity, manage Focus Sessions, and analyze time usage directly from your AI agent.

D View details →
MT

Mustache Template Engine MCP

1 tools Official

Render logic-less Mustache templates with JSON data — the universal spec implemented in 40+ languages. Same template works in JS, Python, Go, Ruby, Rust, and Java.

F View details →
TE

Telnyx MCP

10 tools Official

Send and manage SMS/MMS, check account balances, and configure messaging profiles natively via your AI agent.

A+ View details →
CL

CloudConvert MCP

11 tools Official

Convert files between 200+ formats including PDF, images, video, and documents with a fast cloud-based processing engine.

A+ View details →