Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use Porter with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Orchestrate Kubernetes clusters via Porter. manage apps, projects, container tags, and enforce rollouts directly with your AI.

Included with plan

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 10 capabilities

The complete Porter capability set.

These are the exact actions your AI can choose when you ask it to work with Porter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Porter.

  1. 01

    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

  2. 02

    Get project

    Perform structural extraction of metadata linked to a Porter Project

  3. 03

    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

  4. 04

    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

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Porter.

  1. 05

    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

  2. 06

    Get cluster

    Inspect deep cloud credentials generating a specific K8s Cluster

  3. 07

    List clusters

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

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Porter.

  1. 08

    List environments

    Extract logic isolation environments overlapping the Cluster

  2. 09

    List projects

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

  3. 10

    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

Observed, not estimated

885ms average. Fast in production.

Porter is checked daily against the live service.

Daily averagePeak 1050ms
Aug 20Today
Fastest day
752ms
Slowest day
1050ms
14-day trend
Slowing+11%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Porter, so you can see the experience inside your AI.

It does not authenticate your account with Porter. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Porter Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_97HRl70OC90xV4WamIvMCoFpPgzxIQZ45L5KjFmm/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Porter capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "porter-paas-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_97HRl70OC90xV4WamIvMCoFpPgzxIQZ45L5KjFmm/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

FAQ

Questions Porter owners ask.

  • 01

    Can my AI automatically deploy an urgent hotfix tag?

    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.

  • 02

    Can the agent check internal Helm variables for external addons?

    Absolutely. Using the list_helm_releases capability, your agent analyzes raw orchestrator chart variables inside the cluster's namespace. It is invaluable for diagnosing why your Postgres Helm initialization is misbehaving.

  • 03

    Is it safe to orchestrate infrastructure boundaries with AI?

    Yes! The token you provide is inherently scoped to the exact projects authorized in the Porter Dashboard. The AI strictly respects the platform's isolation, ensuring you only restart or query bounded namespace assets.

Explore

More in Developer Tools

Suggestions