How to Use the Conduit MCP in Vercel AI SDK

Q: How do I connect the Conduit MCP Server to Vercel AI SDK?

Install @ai-sdk/mcp and ai, then use createMCPClient pointing to your Vinkius endpoint. Pass the tools from mcpClient.tools() directly into your streamText function, and always call mcpClient.close() once the execution finishes.

Q: Can my Vercel AI SDK agent trigger a Conduit workflow?

Yes. Your agent uses triggerworkflow by first discovering active IDs with listworkflows. The SDK handles the tool call execution, allowing your agent to kick off the pipeline and stream the confirmation status back to your frontend.

Q: How does Vercel AI SDK handle Conduit connection errors?

The SDK catches execution failures during tool calls like getrunstatus. If a connection drops, the model receives the raw error from the server, allowing it to explain the failure directly to the user in the stream.

Stream Conduit pipeline telemetry directly to your React components in real-time using Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Conduit MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Pipeline Status in Vercel AI SDK

The `get_run_status` tool lets your frontend agent fetch immediate execution metrics for any active data stream. When a user requests a status update, the Vercel AI SDK streams this telemetry word-by-word into your React UI, bypassing typical loading indicators. Your interface renders live updates as the agent pulls run details. By calling `list_workflow_runs` alongside your streaming UI components, you give users a live, scrolling feed of pipeline history that updates without refreshing the page.

Trigger Conduit Workflows from Edge Functions

The `trigger_workflow` tool gives your edge-deployed agent the ability to start data syncs instantly based on user chat commands. Because this MCP Server runs in V8 sandboxes, your Next.js Edge Functions invoke these triggers with sub-millisecond cold starts. Users type a command to kick off a sync, and your agent calls `list_workflows` to find the correct ID before starting the run. The SDK streams the initiation confirmation directly to the client-side chat interface.

Live Connector Auditing in Your App

The `list_available_sources` tool exposes every supported source connector type directly to your streaming AI client. Your frontend agent maps these sources against `list_available_destinations` to show users exactly where their data can flow. Instead of hardcoding connection options, the agent queries active pipelines via `list_connections`. It's a cleaner way to handle dynamic routing, and the Vercel AI SDK renders the active topology in real-time as the model processes the JSON payload.

Setup guide

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

Install `@ai-sdk/mcp` and `ai`, then use `createMCPClient` pointing to your Vinkius endpoint. Pass the tools from `mcpClient.tools()` directly into your `streamText` function, and always call `mcpClient.close()` once the execution finishes.

Yes. Your agent uses `trigger_workflow` by first discovering active IDs with `list_workflows`. The SDK handles the tool call execution, allowing your agent to kick off the pipeline and stream the confirmation status back to your frontend.

The SDK catches execution failures during tool calls like `get_run_status`. If a connection drops, the model receives the raw error from the server, allowing it to explain the failure directly to the user in the stream.

Yes. This server runs on Vinkius V8 isolates, making it compatible with the lightweight HTTP transport required by Edge-deployed Vercel AI SDK projects.

Your pipeline definitions, source credentials, and execution logs never pass through third-party servers. Vinkius executes the server in an ephemeral sandbox, securing your connection strings and destination tokens.

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