How to Use the ChangeDetection.io MCP in Vercel AI SDK

Q: How do I configure ChangeDetection.io with Vercel AI SDK?

Install @ai-sdk/mcp and initialize the client using the HTTP transport pointing to your Vinkius endpoint. Pass the tools from mcpClient.tools() directly into streamText to let your agent call listwatches or createwatch on demand.

Q: Can Vercel AI SDK stream live page diffs from ChangeDetection.io?

Yes, the agent calls getsnapshotdiff using the keywords previous and latest. The Vercel AI SDK streams the resulting text difference directly to your frontend components as it resolves.

Q: How do I manage tags in ChangeDetection.io using Vercel AI SDK?

Your agent uses createtag and listtags to organize monitored URLs. The Vercel AI SDK UI can render these tags as interactive filters, updating the active watch list dynamically.

Feed live website monitoring data directly into your Next.js frontend with Vercel AI SDK and the ChangeDetection.io 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 ChangeDetection.io MCP to Vercel AI SDK

Create your Vinkius account to connect ChangeDetection.io 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 ChangeDetection.io with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render Live Visual Diffs in Your Vercel AI SDK UI

This ChangeDetection.io MCP Server lets your application fetch raw page differences instantly. By invoking `get_snapshot_diff` with previous and latest parameters, your frontend receives the precise text modifications. You feed these diffs straight into the Vercel AI SDK UI components. Users watch the exact HTML or text changes appear line-by-line without waiting for a full page reload or API polling cycle.

Bulk Import and Watch Setup on the Edge

This server exposes `import_urls` to feed bulk targets into your tracking dashboard. Your Edge Functions call this tool to queue up multiple URLs instantly when a user submits a list. The client then runs `create_watch` to set specific tracking parameters for each new target. Because Vercel AI SDK handles streaming tool calls, your interface displays the progress of each created watch in real time.

Instant Change History Retrieval

This toolset uses `get_watch_history` to pull historical capture states for any monitored URL. Your agent parses this timeline to identify how frequently a competitor updates their pricing page. You display this historical sequence using Vercel AI SDK stream helpers. The agent builds a visual timeline on the fly, showing users exactly when changes occurred over the past month.

Setup guide

Set up ChangeDetection.io 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 ChangeDetection.io 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 ChangeDetection.io 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 ChangeDetection.io. 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 ChangeDetection.io 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 ChangeDetection.io MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and initialize the client using the HTTP transport pointing to your Vinkius endpoint. Pass the tools from `mcpClient.tools()` directly into `streamText` to let your agent call `list_watches` or `create_watch` on demand.

Yes, the agent calls `get_snapshot_diff` using the keywords previous and latest. The Vercel AI SDK streams the resulting text difference directly to your frontend components as it resolves.

Yes, this MCP Server works within React Server Components. You call `get_watch` or `get_snapshot` during server-side rendering to fetch the latest website state before delivering the page to the browser.

Your agent uses `create_tag` and `list_tags` to organize monitored URLs. The Vercel AI SDK UI can render these tags as interactive filters, updating the active watch list dynamically.

Your tracked target URLs and HTML snapshots remain private inside the Vinkius V8 Isolate Sandbox. This setup uses a single ephemeral token to authorize requests, meaning your credentials never expose themselves to the frontend client via this MCP link.

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