How to Use the Voiceflow MCP in Vercel AI SDK

Q: How do I handle user input in Voiceflow with Vercel AI SDK?

You send the user's prompt using interact. Your agent client receives this, processes it against the MCP Server tools (like querykb), and returns a stream of text to your React component.

Q: What data types does Voiceflow expose for Vercel AI SDK?

It exposes project details via getproject, conversation history using transcripts, and real-time user state variables accessible through getstate and savestate.

Q: If I need to list existing Voiceflow projects, which tool should I use with Vercel AI SDK?

Use the listprojects tool. This lets your agent client check what conversation flows are available in the system before prompting the user.

Q: Can I get user feedback through Voiceflow using my AI client?

Yes, you can call the getfeedback tool. This allows your application to surface user sentiment or direct input into your operational data stream.

Q: What kind of data privacy information does this MCP Server touch?

This server touches user conversation state/variables and conversation transcripts, which are critical for maintaining context across sessions. Always manage these tokens securely.

Real-time conversational agents in Next.js and React using your AI client.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Voiceflow MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live responses into the UI

Your agent uses `interact` to send messages, and the results stream right into your component. This means users see data appearing instantly—no loading spinners needed. This tool is built for frontends that need high responsiveness. Since it supports Edge Functions, you can handle all the API calls without worrying about backend latency.

Manage conversation state and history

You control how the conversation progresses using tools like `get_state` or updating variables with `save_state`. This gives your agent memory, ensuring it remembers key details from earlier in the chat. Need to reset everything? Just call `delete_state`. You can also pull up past interactions by listing transcripts via `list_transcripts`.

Query knowledge bases directly

The agent needs answers, and this MCP Server gives it two ways: running a search against your documentation using `query_kb`, or getting general details about the source material with `list_kb_docs`. This makes your app smart without needing a full backend indexing service. You can also list available tags using `list_kb_tags` to restrict searches, giving you precise control over what information gets returned.

Setup guide

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

You send the user's prompt using `interact`. Your agent client receives this, processes it against the MCP Server tools (like `query_kb`), and returns a stream of text to your React component.

It exposes project details via `get_project`, conversation history using transcripts, and real-time user state variables accessible through `get_state` and `save_state`.

Use the `list_projects` tool. This lets your agent client check what conversation flows are available in the system before prompting the user.

Yes, you can call the `get_feedback` tool. This allows your application to surface user sentiment or direct input into your operational data stream.

This server touches *user conversation state/variables* and *conversation transcripts*, which are critical for maintaining context across sessions. Always manage these tokens securely.

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