How to Use the Chatwoot MCP in Vercel AI SDK

Q: How does the Vercel AI SDK connect to the Chatwoot MCP server?

You use createMCPClient and pass it the Vinkius URL for your server. Then, you get the available tools from mcpClient.tools() and provide them to the generateText or streamText functions. Just be sure to call mcpClient.close() when you're done.

Stream Chatwoot data directly into your React components. Build live customer support UIs 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 Chatwoot MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live-Stream Chat History

This tool lets you pull the full message history for any conversation. When you pair `get_chat_history` with the Vercel AI SDK, the data streams directly into your frontend. Your users see the conversation appear message by message, not all at once after a loading spinner. This makes your UI feel alive. Instead of a static data dump, you can build components that populate in real time. Combine it with `get_contact_details` to stream a customer's profile into a sidebar while their conversation history loads right next to it.

Build Custom Support Dashboards with this MCP Server

Your Next.js app can now have its own customer support panel. Use this MCP server to pull agent lists, inboxes, and active conversations directly from your Chatwoot account. Your agent can ask for the data, and the tools fetch it instantly. Populate your custom UI with data from `list_support_agents`, `list_chatwoot_inboxes`, and `list_woot_conversations`. The AI isn't just a chatbot in the corner; it becomes the data source that powers your entire application, streaming information as it's requested.

Send Replies from Your Own UI

This isn't just for reading data. You can build an interface where a support manager reviews a conversation and asks the AI to send a reply. The `send_chat_message` tool posts the message directly to the customer in Chatwoot. Because the Vercel AI SDK can stream tool status, your UI can give immediate feedback. Show a “Sending…” state while the message is in flight, then switch to “Sent.” You're building a true command interface for your support operations, not just a data viewer.

Setup guide

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

You use `createMCPClient` and pass it the Vinkius URL for your server. Then, you get the available tools from `mcpClient.tools()` and provide them to the `generateText` or `streamText` functions. Just be sure to call `mcpClient.close()` when you're done.

Yes, that's exactly what this is for. The SDK is designed to stream data from tools like `get_chat_history`, letting you update your React or Svelte UI instantly. Your dashboard will feel fast because you don't have to wait for the full API response.

You could build custom interfaces for support agents, internal admin panels showing conversation stats, or a tool for your sales team to look up customer history. Since results stream, the UI is very responsive, which is great for interactive applications.

Once connected to the MCP server, you can programmatically list all the tools. The available tools let you read contacts, conversations, and inboxes, as well as send new messages directly into a conversation.

Your Chatwoot conversation data and contact details are streamed through an ephemeral, sandboxed environment. Vinkius proxies the request using your endpoint token but never stores the message content or customer information. The entire connection is torn down after the request completes.

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