How to Use the Codefresh MCP in Vercel AI SDK

Stream Codefresh build logs and pipeline states directly into your Vercel AI SDK frontends for live status updates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Codefresh MCP to Vercel AI SDK

Create your Vinkius account to connect Codefresh 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 Codefresh with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor pipelines in Vercel AI SDK

Feed your UI real-time CI/CD data by calling `list_codefresh_pipelines` and `list_codefresh_builds`. Your users get an immediate look at current deployment statuses without leaving your dashboard. This MCP Server pushes status updates as they happen. You won't deal with stale data or manual refreshes in your React or Next.js components.

Start builds from your interface

Trigger new deployments by wiring `trigger_codefresh_build` into your application buttons. Your end users can kick off workflows based on logic you define in your edge functions. It removes the friction of switching between tabs to manage releases. Everything stays inside the product you built.

Inspect delivery clusters live

Use `list_delivery_clusters` to show your users exactly where their code lives. This tool gives you the raw data to build status badges or cluster health indicators in your app. Your frontend acts as a window into your infrastructure. It keeps the user informed about cluster connectivity and deployment targets.

Setup guide

Set up Codefresh 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 Codefresh 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 Codefresh 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 Codefresh. 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 Codefresh 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 Codefresh MCP in Vercel AI SDK

Install the necessary packages and initialize the client using the provided endpoint. You then pass the tools from the server directly into your generateText calls to start interacting with your pipelines.

Yes, you can map the trigger tool to a UI action. When a user clicks a button, your SDK sends the request to the server, which initiates the build immediately.

The server results flow back through your stream handlers. You get the data in your UI as soon as the tool completes its execution.

The server returns the specific error details. You can catch these in your code to show a clear alert to the person using your app.

Your pipeline configurations and build logs are encrypted in transit. We only expose the specific metadata requested by your agent during a session.

Use it with your favorite AI tools

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

OpenAI Agents SDK sdk-python