How to Use the Fastn MCP in Vercel AI SDK

Q: How do I stream Fastn execution logs using Vercel AI SDK?

You pass executeflow and getexecution directly to the streamText function. As the Vercel AI SDK processes the tool calls, it streams the JSON payloads directly to your UI components, showing users each completed step in real-time.

Q: Can I build a visual workflow builder in Next.js with Fastn and Vercel AI SDK?

Yes, you can. Use listworkflows to pull existing designs and updateworkflow to save modifications. The SDK handles the client-side rendering while the server manages backend state.

Stream Fastn workflow steps and live execution states directly into your Vercel AI SDK frontend without loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fastn MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live execution steps to the browser

This Fastn MCP Server lets your Vercel AI SDK client spin up and monitor backend automations while feeding raw status updates straight to your React or Next.js frontend. When you kick off a flow with `execute_flow`, the step-by-step execution details stream over the wire in real time. Users watch their tasks run live instead of staring at a blank screen. If something gets stuck, your application can pull the full run history using `get_execution` or cancel the operation immediately with `cancel_execution` using simple Edge-compatible TypeScript calls.

Manage workflow lifecycles from Next.js Edge routes

Fastn provides a clean API to build, update, and deploy low-code workflows directly from your application's edge middleware. By passing `create_workflow` and `update_workflow` to your MCP tool array, your agent can modify running backend tasks on the fly. No more redeploying your entire codebase just to change a conditional branch. Once your agent finishes drafting the changes, it calls `publish_workflow` to push the updates live instantly while tracking usage limits via `get_quota_usage`.

Secure credential storage for Vercel AI SDK agents

Fastn handles the heavy lifting of storing and rotating API keys for external services so your frontend code never exposes sensitive secrets. Your Vercel AI SDK agent uses `store_credentials` to lock down connector configurations securely behind a single Vinkius endpoint token. When your backend workflows run, they pull these secrets safely. If an API key expires, the agent runs `rotate_credentials` to update the connection details without exposing the raw keys to the browser session.

Setup guide

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

You pass `execute_flow` and `get_execution` directly to the `streamText` function. As the Vercel AI SDK processes the tool calls, it streams the JSON payloads directly to your UI components, showing users each completed step in real-time.

Yes, you can. Use `list_workflows` to pull existing designs and `update_workflow` to save modifications. The SDK handles the client-side rendering while the server manages backend state.

The MCP client setup is lightweight and does not rely on Node.js-only APIs. You can initialize the connection and run tools like `list_executions` directly within your Edge Function middleware routes.

You should monitor your consumption metrics programmatically. Use `get_quota_daily` or `get_quota_summary` to track your current volume and prevent your edge functions from hitting hard API limits.

Your third-party API keys are stored in an isolated, encrypted vault. When you use `get_credentials`, the server handles the handshake over a zero-trust channel, ensuring your keys never touch the Vercel client-side environment.

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