How to Use the Concord (Workflow Orchestration) MCP in Vercel AI SDK

Q: How do I stream live logs from Concord (Workflow Orchestration) using Vercel AI SDK?

Call getprocesslog inside your streamText function. Pass the tools from your MCP client, allowing the model to yield log chunks directly to your Next.js UI component.

Q: How do I handle connection timeouts during long-running Concord tasks?

Always call mcpClient.close() when your stream finishes. This prevents open connections from hanging in your MCP setup while waiting for getprocess to return.

Q: Is Concord (Workflow Orchestration) data private when using Vercel AI SDK?

All logs fetched via getprocesslog and project data from getprojectdetails stay within your Vercel deployment and your self-hosted Concord instance. Vinkius acts as a secure tunnel, meaning your raw build logs and environment credentials never get stored or inspected.

Stream Concord (Workflow Orchestration) logs and process states straight to your Vercel AI SDK frontend in real time.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Concord (Workflow Orchestration) MCP to Vercel AI SDK

Create your Vinkius account to connect Concord (Workflow Orchestration) 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 Concord (Workflow Orchestration) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Pipeline Monitoring with Vercel AI SDK

Let your users watch CI/CD pipelines run in real-time. Instead of staring at a blank screen, your frontend streams live execution output directly from `get_process_log` as this MCP Server executes the work. Your application calls `list_running_processes` to populate a live dashboard, letting users watch active jobs without waiting for full page reloads. The SDK pipes this data straight to React components the second the server responds.

Instant Process Control via Edge Functions

Stop runaway builds immediately from any edge-rendered UI. Your agent evaluates the log stream and triggers `terminate_process` the moment a test suite fails, saving expensive compute cycles on your self-hosted Concord runner. Users can kick off fresh deployments with a button click. The agent uses `start_process` behind the scenes, immediately feeding the new process ID to the UI so the user sees the build status change instantly.

Dynamic Org and Project Mapping

Build a clean interface that maps out complex CI/CD structures. The agent queries `list_organizations` and `list_projects` to build a clean sidebar navigation for your users, rendering Concord's structure dynamically. When a user clicks a project, the SDK pulls repository configurations via `list_repositories` and project metadata using `get_project_details`. This allows your AI-driven interface to display configuration details without lag.

Setup guide

Set up Concord (Workflow Orchestration) 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 Concord (Workflow Orchestration) 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 Concord (Workflow Orchestration) 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 Concord. 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 Concord (Workflow Orchestration) 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 Concord (Workflow Orchestration) MCP in Vercel AI SDK

Call `get_process_log` inside your `streamText` function. Pass the tools from your MCP client, allowing the model to yield log chunks directly to your Next.js UI component.

Yes, the client connects over standard HTTP transport, which runs perfectly on Edge runtimes. Your agent can call `start_process` or check status via `get_process` without cold-start delays.

No, you do not need to write poll loops. Your Vercel AI SDK agent can repeatedly call `list_running_processes` or check logs dynamically based on the streaming UI needs.

Always call `mcpClient.close()` when your stream finishes. This prevents open connections from hanging in your MCP setup while waiting for `get_process` to return.

All logs fetched via `get_process_log` and project data from `get_project_details` stay within your Vercel deployment and your self-hosted Concord instance. Vinkius acts as a secure tunnel, meaning your raw build logs and environment credentials never get stored or inspected.

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