How to Use the Coolify MCP in Vercel AI SDK

Q: How do I handle Coolify deployment errors inside Vercel AI SDK?

The server returns raw error logs from triggerdeployment directly to your agent. You can catch these errors in your stream and render custom fallback UI blocks for Nixpacks build failures.

Q: Can I use Vercel AI SDK to monitor multiple Coolify servers?

Yes. The listservers tool returns all self-hosted Docker swarm nodes, and the SDK processes this array to let users switch between server contexts in your dashboard.

Q: Does Vercel AI SDK support manual container restarts on Coolify?

Absolutely. You call restartapplication within your tool definitions, which bounces the target container and returns the updated state to the client interface.

Q: How do I map project repositories using this MCP Server?

Run listapplications to get the complete dictionary of active project repositories and their UUIDs. Your agent uses these UUIDs to target specific containers for updates.

Pipe real-time Coolify deployment states and server metrics directly into your React components using the Vercel AI SDK MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Coolify MCP to Vercel AI SDK

Create your Vinkius account to connect Coolify to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Coolify with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time Deployment Streaming via Vercel AI SDK

This MCP Server exposes `trigger_deployment` so your frontend triggers Git-based builds and updates the UI block by block as Nixpacks compiles. Users watch the build logs render live in their browser without manual refresh cycles. By integrating `get_application` into your edge routes, the SDK handles server-sent events to show active Traefik FQDN paths the second they resolve. You write standard React hooks while the underlying system handles the SSH handshakes and container status polls.

Live Database Provisioning Feedback

The `get_database` tool pulls active connection configurations and maps them to your backend UI instantly. When your user requests a new PostgreSQL or Redis instance, the SDK feeds the progress bar straight from the Docker swarm. Running `list_databases` lets your interface show connection strings and backup schedules without API lag. Your agent handles the state updates, keeping the local UI in sync with the actual Coolify database bounding boxes.

Immediate Container Control

Use `restart_application` through this MCP Server to recycle containers and apply new environment variables directly from an interactive chat interface. The SDK pipes the container exit codes and startup status right back to the user viewport. If a security incident occurs, your code calls `stop_application` to restrict web ingress immediately. The user gets instant visual confirmation that the mapped Docker containers stopped running on the host node.

Setup guide

Set up Coolify MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Coolify tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Coolify transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Coolify. 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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Coolify now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Coolify MCP in Vercel AI SDK

The server returns raw error logs from `trigger_deployment` directly to your agent. You can catch these errors in your stream and render custom fallback UI blocks for Nixpacks build failures.

Yes. The `list_servers` tool returns all self-hosted Docker swarm nodes, and the SDK processes this array to let users switch between server contexts in your dashboard.

Absolutely. You call `restart_application` within your tool definitions, which bounces the target container and returns the updated state to the client interface.

Run `list_applications` to get the complete dictionary of active project repositories and their UUIDs. Your agent uses these UUIDs to target specific containers for updates.

All sensitive data, including PostgreSQL connection strings, SSH port mappings, and Traefik reverse proxy paths, remains inside the secure Vinkius sandbox. This connector never stores your credentials, passing them directly to your local runtime via secure environment variables.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript