Zeabur PaaS Deployment MCP. Deploy services and send emails from chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Zeabur (PaaS Deployment) MCP Server lets your AI agent manage cloud services and containers without leaving your chat. You can deploy new code using YAML templates, run shell commands inside live service containers, fetch build logs for debugging, or send personalized transactional emails—all from one place.
What your AI agents can do
Create upload stage
Creates an upload stage necessary for deploying pre-packaged applications to the service.
Deploy template
Deploys a new service directly using a raw YAML specification template.
Download file
Fetches and downloads any specific file from an active service container's environment.
Deploy services using YAML templates, package applications, and prepare deployments through dedicated stages.
Execute arbitrary shell commands inside live containers or download specific files from them for review.
Retrieve detailed, live build logs to pinpoint exactly where a deployment failed.
Trigger single or batch transactional emails using the Zeabur Email API infrastructure.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Zeabur (PaaS Deployment) MCP Server: 9 Tools for DevOps Ops
Use these nine tools to manage deployment templates, execute commands in containers, download files, and send transactional emails via your AI agent.
019e5d69create upload stage
Creates an upload stage necessary for deploying pre-packaged applications to the service.
019e5d69deploy template
Deploys a new service directly using a raw YAML specification template.
019e5d69download file
Fetches and downloads any specific file from an active service container's environment.
019e5d69execute command
Runs a shell command within the live environment of a specified service container.
019e5d69get build logs
Retrieves real-time build logs associated with a specific deployment run for debugging.
019e5d69prepare deployment
Finalizes and prepares an application deployment after necessary files have been uploaded to the stage.
019e5d69schedule email
Schedules a personalized email to be sent at a future time using your Zeabur Email Token.
019e5d69send batch emails
Sends multiple personalized emails simultaneously to a list of recipients via the Zeabur Email API.
019e5d69send email
Immediately sends a single, transactional email using your Zeabur Email Token.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Zeabur (PaaS Deployment), then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Your AI agent takes charge of cloud services when you connect it to Zeabur. You manage deployment pipelines, container environments, and outbound emails—all from your chat window.
Deployment Management
You run deploy_template and drop in raw YAML specs to get a new service up fast. If the application is pre-packaged, first you gotta call create_upload_stage to set up the necessary upload area for the build files, then you use prepare_deployment when you're ready to commit everything.
Container Control and Debugging
You don't just look at logs; you interact with the running code itself. You run execute_command to fire off arbitrary shell commands inside a live service container for testing or checks, and you use download_file to pull specific files out of that container environment when you need them for review.
If anything breaks during deployment, don't guess what went wrong; you run get_build_logs and pull the real-time build output right into your chat so you know exactly where it crashed.
Transactional Communications
You handle personalized messages using the Zeabur Email API infrastructure. You use send_email to send a single, immediate transactional email when you need it now. For groups of people, you run send_batch_emails to fire off multiple personalized emails simultaneously across a list of recipients, and if you gotta plan ahead, you use schedule_email to set up a message that'll go out at a future time.
How Zeabur PaaS Deployment MCP Works
- 1 Subscribe to this server and provide your Zeabur API Token (and optionally, your Email Token).
- 2 Tell your AI agent what you need—for example: 'Deploy the service using this YAML.'
- 3 The agent calls the appropriate tool (
deploy_template,send_email, etc.), executes the task against your cloud account, and reports the outcome back to you.
The bottom line is that it lets you manage complex PaaS resources—deployment, containers, email—all through simple conversation with your agent.
Who Is Zeabur PaaS Deployment MCP For?
This server is for the backend developer who gets tired of context-switching between their IDE, the terminal, and a browser dashboard. It's for the DevOps engineer who needs to roll back a service or check logs without logging into the cloud console. If your job involves deploying code and sending notifications, this saves you hours.
Running deploy_template after a merge and using get_build_logs to validate the build process without leaving their CI/CD dashboard.
Triggering a service update via create_upload_stage and then immediately sending a confirmation email using send_email.
Automating the delivery of post-deployment alerts by managing container files (download_file) and scheduling follow-up emails with schedule_email.
What Changes When You Connect
- Saves time on deployment debugging. Instead of jumping to a web console, you just ask the agent to run
get_build_logsand get the output immediately. Pinpoint failures faster. - Eliminates manual container access. Need to check a config file? Use
execute_commandordownload_fileto pull it directly into your chat window without SSHing in. - Streamlines complex releases. The agent manages the full flow: upload files via
create_upload_stage, then runprepare_deployment, and finally deploy usingdeploy_template. It's a single sequence of commands. - Manages communications alongside code. After deployment, you can send confirmation alerts instantly. Use
send_emailfor immediate notification orschedule_emailif the message needs to wait until business hours. - Handles bulk tasks efficiently. Forget sending one email at a time. Use
send_batch_emailsto hit dozens of recipients with personalized messages, all triggered by your agent.
Real-World Use Cases
Post-Deployment Health Check and Alert
A full-stack developer just finished deploying a new microservice. They ask the agent to first run get_build_logs to confirm success. Next, they tell it to execute a status check command via execute_command. Finally, they use send_email to alert the team that the service is live and running.
Automating Onboarding Follow-ups
An operations engineer needs to send welcome kits. Instead of manually writing emails, they give the agent a list and ask it to use send_batch_emails with personalized content. This happens right after a successful deployment triggered by deploy_template.
Debugging Missing Dependencies
The service container fails because a dependency is missing. The agent runs get_build_logs, identifies the failing command, and then uses download_file to pull the package manifest so the developer can fix it locally before retrying.
Scheduled Reporting Pipeline
A backend team needs a weekly digest. They instruct the agent to run a full deployment check (using deploy_template) and then use schedule_email to deliver the summary report every Monday morning at 8 AM.
The Tradeoffs
Debugging logs via copy/paste
The build fails, so the developer manually navigates to the Zeabur dashboard, clicks 'Logs,' and copies a giant block of text into Slack. The information is messy and hard to read.
→
Just ask your agent to run get_build_logs. It pulls the logs directly into the conversation thread, making it instantly visible and actionable for everyone.
Manual file retrieval from containers
The service breaks because a required configuration file is missing. The engineer has to remember which container, navigate to its directory in the UI, and manually download the file.
→
Use download_file. You tell your agent exactly what file you need (e.g., 'config/api-key.json'), and it fetches it straight into the chat for you.
Sending multiple confirmation emails
The service deploys successfully, but the team lead has to manually write and send 15 separate follow-up emails confirming success.
→
Use send_batch_emails. Give your agent the list of recipients and a template, and it handles the personalized sending in one step.
When It Fits, When It Doesn't
Use this server if your workflow requires coordinating multiple distinct steps: deploying code (YAML templates), running system commands inside containers, reading build logs, or managing structured communications like emails. This is for integrated pipelines.
Don't use it if you only need to write a simple webhook payload, or if the service you are controlling is entirely outside of Zeabur's PaaS ecosystem (e.g., a completely separate AWS S3 bucket). For pure messaging, consider a dedicated message queue connector; for general cloud control, look into multi-cloud orchestration tools that focus on abstracting away specific vendor APIs.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Zeabur. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 9 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Debugging deployments shouldn't require leaving your chat window.
Right now, when a deployment fails, you have to switch context. You jump from the code editor to the CI/CD dashboard, click through multiple tabs (logs, build output, status), and manually copy snippets of text just to figure out if it was an npm dependency issue or a misconfigured environment variable.
With this MCP server, that whole process is gone. You ask your agent for `get_build_logs`. It pulls the real-time console output straight into your chat thread. You see the failure point, and you're done—no dashboard hopping required.
Zeabur PaaS Deployment: Control containers from chat.
Before, if a service failed unexpectedly, checking the internal state was a pain. You had to SSH into the container, figure out the right directory, and then run `ls -la` or manually check log files for evidence of what went wrong—a tedious mess of terminal commands.
Now you can use `execute_command`. You tell your agent exactly which command to run (like 'cat /app/config.yaml'), and it runs it directly against the live container, giving you the output instantly. It's that simple.
Common Questions About Zeabur PaaS Deployment MCP
How do I deploy a service using `deploy_template`? +
You provide the YAML specification to your agent and ask it to run deploy_template. The agent sends the definition to Zeabur, starting the deployment process in your project.
Can I check files inside a container with `download_file`? +
Yes. You specify the path and name of the file you need from the running service container, and the agent fetches that specific binary or config file for you to inspect.
What is the difference between `send_email` and `send_batch_emails`? +
send_email sends one message immediately. Use it when you have a single alert to send out. Reserve send_batch_emails for sending personalized messages to multiple people at once.
How do I get deployment logs using `get_build_logs`? +
You give the agent the specific deployment ID or service name and ask it to retrieve build logs. The output shows the full console activity, helping you track down failure points.
Why does running `send_email` require a dedicated Zeabur Email Token? +
You must provide the specific ZEABUR_EMAIL_TOKEN. This token authorizes your agent to access and send messages through the Zeabur Email REST API, keeping your credentials separate from your main PaaS deployment keys.
Does `execute_command` restrict the types of shell commands I can run? +
No. The tool runs standard shell commands within the container environment. You can use typical Linux utilities like ls, grep, or other system tools relevant to your service’s setup.
Does calling `create_upload_stage` automatically prepare my application for deployment? +
No, creating the stage just reserves space. After you call create_upload_stage, you must also execute prepare_deployment to finalize the package and make it ready for a live service deploy.
Is there a time limit or constraint when using `schedule_email`? +
The scheduling window depends on Zeabur's operational limits. You pass a specific timestamp, and the system manages the queueing; always check the official documentation for maximum lead times.
Can I run shell commands inside my running services? +
Yes! Use the execute_command tool by providing the Service ID, Environment ID, and the command array (e.g., ["ls", "-la"]). Your agent will return the output from the container.
How do I debug a failed deployment using this server? +
You can use the get_build_logs tool with the Project ID and Deployment ID. It will fetch the logs so your AI can analyze the errors and suggest fixes.
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.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
TestLink
Navigate your self-hosted TestLink instance to inspect test plans, suites, cases, and builds natively via your AI agent.
Apify Alternative
Manage your cloud automation — audit actors, tasks, and datasets via AI.
Zentitle2
Manage software licenses and entitlements with a cloud platform that handles activation, metering, and feature gating for ISVs.
You might also like
Blockdaemon (Blockchain Infrastructure)
Access institutional-grade blockchain data across multiple protocols — list blocks, track transactions, and retrieve financial reports via Blockdaemon Ubiquity.
Prometheus
Monitor your infrastructure with Prometheus — run PromQL queries, analyze metrics, and manage time-series data directly from your AI agent.
Freshworks
Manage unified CRM and support via Freshworks — track sales deals and accounts, handle helpdesk tickets, and manage contacts directly from any AI agent.