How to Use the Harness MCP in Vercel AI SDK

Q: Can the Vercel AI SDK harness Harness secrets safely?

Yes, but keep access restricted. Use listsecrets only when necessary and ensure your auth provider limits the agent's scope to specific projects.

Q: How to harness Harness pipeline lists in Vercel AI SDK?

Call the listpipelines tool within your agent logic. The result returns as a clean array you can map directly into a dropdown or list view.

Stream real-time Harness pipeline data directly into your UI components with the Vercel AI SDK for instant visibility.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Harness MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time pipeline monitoring in your UI

Pipe live execution data straight into your frontend components. Use `get_execution_status` to show users exactly which step is running without waiting for a full page refresh. Your app state updates as the CI/CD job progresses. This gives users immediate feedback while the Harness MCP server handles the heavy lifting in the background.

Trigger deployments from your React dashboard

Give your users buttons that actually push code. When a user clicks deploy, your app triggers `execute_pipeline` to start the build process immediately. Everything stays within your app environment. The AI client handles the authentication, so your users never need to touch the Harness console.

Audit logs for your end users

Expose platform history directly in your user-facing admin panels. Fetch logs via `get_audit_logs` to show who changed what and when. This provides transparency without forcing users to leave your product. You get a clean interface while keeping the backend logic strictly inside the MCP server.

Setup guide

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

Connect the server via the MCP client transport and pass the tools to your `generateText` function. This makes the data available to your agent for real-time processing.

Yes, but keep access restricted. Use `list_secrets` only when necessary and ensure your auth provider limits the agent's scope to specific projects.

Call the `list_pipelines` tool within your agent logic. The result returns as a clean array you can map directly into a dropdown or list view.

It does. Since the MCP server communicates over HTTP, your Edge Functions can talk to it without blocking the main event loop.

Your Harness environment data stays between your client and your infrastructure. No external party sees your pipeline YAML or service configurations.

Use it with your favorite AI tools

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