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

Use Zeabur with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Deploy services, manage containers, and send transactional emails via Zeabur PaaS directly from your AI agent.

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 · 9 capabilities

The complete Zeabur capability set.

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

Capability set01 / 03

01-03

3 capabilities in this set.

Part of 9 available through Zeabur.

  1. 01

    Create upload stage

    Create an upload stage for deploying pre-packaged applications

  2. 02

    Deploy template

    Deploy a service using a template specification YAML

  3. 03

    Download file

    Download a file from a service container

Capability set02 / 03

04-06

3 capabilities in this set.

Part of 9 available through Zeabur.

  1. 04

    Get build logs

    Retrieve build logs for a deployment

  2. 05

    Send email

    Requires ZEABUR_EMAIL_TOKEN. Send a single transactional email via Zeabur Email

  3. 06

    Execute command

    Run a command within a service container

Capability set03 / 03

07-09

3 capabilities in this set.

Part of 9 available through Zeabur.

  1. 07

    Prepare deployment

    Prepare a deployment after uploading a file

  2. 08

    Schedule email

    Requires ZEABUR_EMAIL_TOKEN. Schedule an email to be sent later via Zeabur Email

  3. 09

    Send batch emails

    Requires ZEABUR_EMAIL_TOKEN. Send batch personalized emails via Zeabur Email

Observed, not estimated

897ms average. Fast in production.

Zeabur is checked daily against the live service.

Daily averagePeak 1127ms
Aug 22Today
Fastest day
799ms
Slowest day
1127ms
14-day trend
Improving-29%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 9 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 Zeabur, so you can see the experience inside your AI.

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

Zeabur Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_C259WqFoZVL0U3fl3UAYmeTpTKhOp70hGTqhzXJ5/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 — Zeabur capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "zeabur-paas-deployment-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_C259WqFoZVL0U3fl3UAYmeTpTKhOp70hGTqhzXJ5/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 Zeabur owners ask.

  • 01

    Can I run shell commands inside my running services?

    Yes! Use the execute_command capability by providing the Service ID, Environment ID, and the command array (e.g., ["ls", "-la"]). Your agent will return the output from the container.

  • 02

    How do I debug a failed deployment using this server?

    You can use the get_build_logs capability with the Project ID and Deployment ID. It will fetch the logs so your AI can analyze the errors and suggest fixes.

  • 03

    Does this support deploying pre-packaged ZIP files?

    Yes. First, use create_upload_stage to get a presigned URL and upload ID. After uploading your file, use prepare_deployment to trigger the actual deployment process.

Explore

More in Developer Tools

Suggestions