How to Use the Dify MCP in Vercel AI SDK

Q: How do I handle authentication when connecting Dify to Vercel AI SDK?

You pass your Dify API keys securely using the authProvider option in the createMCPClient setup. This keeps credentials out of your client-side bundle and runs safely within Vercel's Edge runtime.

Q: Can I stream tool calls from Dify directly using the Vercel AI SDK?

Yes, you can. By passing the tools resolved from mcpClient.tools() into streamText, the Vercel AI SDK streams both the text generation and the underlying tool executions to your UI.

Q: How do I close the connection to prevent memory leaks?

Always call mcpClient.close() once your stream finishes or when your edge execution context terminates. This prevents dangling HTTP connections from piling up on your serverless instances.

Q: How does this setup secure my uploaded files and chat logs?

All file uploads via uploadfile and chat histories fetched via listmessages pass through an ephemeral, zero-trust V8 sandbox. Your raw document bytes and message text are never cached, stored, or analyzed by the marketplace hosting layer.

Stream real-time Dify agent workflows directly into your Next.js or React UI with the 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 Dify MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live Dify Chat to React via Vercel AI SDK

The `chat` tool connects your Vercel AI SDK streaming interface directly to Dify agent endpoints. Instead of making users wait for a slow backend response, this tool pipes the agent's reasoning steps and raw output straight to your frontend. You import the tool, pass it to `streamText`, and watch the live feed resolve. Handling state updates becomes trivial because the Vercel AI SDK handles the stream chunking for you. You do not need to write custom WebSockets or polling loops. The end user sees the actual text generation instantly, keeping engagement high while reducing perceived latency.

Audit App Configs with this MCP Server

The `get_parameters` tool retrieves runtime application configurations directly inside your Edge Functions. This MCP Server tool exposes the active model settings, prompt templates, and system rules without exposing your secret master keys to the client side. Your Vercel AI SDK code queries this metadata during the initial handshake. Running this check at the edge ensures you load parameters in under 50ms. You can dynamically adjust your UI layout or system prompts based on what the Dify backend returns. This approach keeps your frontend synchronized with your agent's actual capabilities.

Manage Files and History in Next.js Server Actions

The `upload_file` and `list_conversations` tools handle document ingestion and historic session retrieval within your Next.js server actions. Users drop files into your React component, and the Vercel AI SDK forwards the raw bytes directly to Dify's storage layer. From there, your agent accesses the document context immediately. To populate the sidebar, you fetch previous sessions using `list_messages`. This keeps the UI state hydrated with accurate chat history. You don't have to build a parallel database to track what the agent and user discussed.

Setup guide

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

You pass your Dify API keys securely using the `authProvider` option in the `createMCPClient` setup. This keeps credentials out of your client-side bundle and runs safely within Vercel's Edge runtime.

Yes, you can. By passing the tools resolved from `mcpClient.tools()` into `streamText`, the Vercel AI SDK streams both the text generation and the underlying tool executions to your UI.

The MCP Server packages complex multi-step routines like file uploading and conversation history retrieval into type-safe tools. You avoid writing boilerplate fetch requests and manual error handling in your Next.js API routes.

Always call `mcpClient.close()` once your stream finishes or when your edge execution context terminates. This prevents dangling HTTP connections from piling up on your serverless instances.

All file uploads via `upload_file` and chat histories fetched via `list_messages` pass through an ephemeral, zero-trust V8 sandbox. Your raw document bytes and message text are never cached, stored, or analyzed by the marketplace hosting layer.

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