How to Use the Chattermill MCP in Vercel AI SDK

Q: How do I connect the Chattermill MCP Server to my Vercel AI SDK project?

Install @ai-sdk/mcp and ai via npm. Initialize the connection using createMCPClient with your Vinkius HTTP URL, and pass the tools directly into streamText or generateText.

Q: Can I stream Chattermill metrics live to a React component using AI SDK?

Yes, you can. By passing the tools returned from mcpClient.tools() to streamText, your UI renders the metrics in real-time as the model fetches them.

Q: Do I need to close the MCP connection in my Next.js API routes?

Yes, you must always call mcpClient.close() when your execution finishes. This prevents hanging HTTP connections and ensures your serverless functions spin down cleanly.

Stream live customer sentiment metrics directly into your Next.js frontend with Vercel AI SDK and the Chattermill MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chattermill MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream real-time sentiment metrics in AI SDK

The `get_chattermill_metric` tool pulls calculated NPS, CSAT, volume, and sentiment scores directly into your live application. You feed this data straight into your streaming UI components so users watch live customer health metrics render without waiting for a full page reload. First, locate your target project using `list_chattermill_projects` to grab the key. Then, pass that key to retrieve real-time trends that your frontend can render immediately via this MCP connection.

Feed customer feedback directly into edge functions

The `list_feedback_responses` tool fetches raw customer comments and scores to fuel your edge-deployed AI client. Running on Vercel Edge Functions means you process these feedback loops with minimal latency, passing raw customer text directly into your LLM pipelines. You can filter the incoming stream by date or pagination using this endpoint. Combine it with `get_response_details` to extract specific theme mappings and metadata for any single piece of feedback without hitting database bottlenecks.

Discover AI-generated customer themes on the fly

The `list_feedback_themes` tool exposes the underlying topics and categories that Chattermill automatically detects in customer messages. Your AI client reads these themes to dynamically build UI filters or sort customer complaints into distinct buckets right inside your app. To organize these topics hierarchically, use `list_theme_categories` alongside the main theme list. This lets you build dynamic navigation menus in your React frontend where users click through high-level issues to see the exact feedback driving them.

Setup guide

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

Install `@ai-sdk/mcp` and `ai` via npm. Initialize the connection using `createMCPClient` with your Vinkius HTTP URL, and pass the tools directly into `streamText` or `generateText`.

Yes, you can. By passing the tools returned from `mcpClient.tools()` to `streamText`, your UI renders the metrics in real-time as the model fetches them.

Vinkius manages the API keys for you behind a single secure endpoint token. You pass this token during the `createMCPClient` setup, and the SDK handles the rest without exposing raw Chattermill credentials.

Yes, you must always call `mcpClient.close()` when your execution finishes. This prevents hanging HTTP connections and ensures your serverless functions spin down cleanly.

All customer feedback comments, NPS scores, and theme classifications pass through a secure V8 Isolate Sandbox on Vinkius. This ephemeral environment guarantees that your raw feedback text is never cached or stored on intermediate servers, maintaining absolute data privacy.

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