How to Use the ChangeDetection.io MCP in OpenAI Agents SDK

Q: Can my agent manage multiple watches at once?

Yes. Your agent can listwatches to see everything it's monitoring. It can also use importurls to create a batch of new watches from a list, which is a lot faster than creating them one by one.

Q: Is there a way to search for a specific watch with my ChangeDetection.io and OpenAI Agents SDK setup?

Absolutely. The searchwatches tool is built for this. Your agent can search by URL, title, or tags you've assigned, making it easy to find and manage a specific watch even among hundreds of others.

Build production agents with the OpenAI Agents SDK that monitor any site for changes, backed by ChangeDetection.io's automated checks.

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 OpenAI Agents SDK

Create your Vinkius account to connect ChangeDetection.io to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Give your agents eyes on the web

Your OpenAI agent can now `create_watch` on any URL and get alerts when the content changes. It's not just a notification. Your agent can analyze the change using `get_snapshot_diff` and decide the next action based on its own logic. This is how you build autonomous systems that react to the real world, not just internal data. The built-in guardrails in the OpenAI Agents SDK ensure your agent won't go off the rails deleting watches or creating duplicates without your explicit approval. This MCP Server gives it the tools to see.

Organize your monitoring at scale

A flat list of URLs doesn't scale. Let your agent use `create_tag` and `list_tags` to group watches by project, priority, or any other system you devise. It's a simple, effective way to manage complexity. When it's time to act, your agent can `search_watches` by tag to find exactly what it needs. You can manage hundreds of monitored sites without the whole thing turning into a mess. It's about giving your agent tools for proper information management.

Let your OpenAI Agents SDK agent see the past

A single change is one thing, but a trend is another. With `get_watch_history`, your agent can pull the full record of changes for a specific site. It can then grab individual snapshots with `get_snapshot` to perform deeper analysis or build a timeline of modifications. This isn't just about 'what changed'. It's about giving your agent the context to understand *how* a site has evolved over time. That's the difference between simple alerting and actual intelligence.

Setup guide

Set up ChangeDetection.io MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all ChangeDetection.io tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives ChangeDetection.io tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate ChangeDetection.io tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="ChangeDetection.io Agent",
            instructions="You have access to ChangeDetection.io tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

It's straightforward. You'll instantiate the MCP Server with your Vinkius endpoint URL and pass it into your Agent's constructor. The OpenAI Agents SDK automatically discovers all the available tools like `create_watch` and `get_snapshot_diff`.

Yes. Your agent can `list_watches` to see everything it's monitoring. It can also use `import_urls` to create a batch of new watches from a list, which is a lot faster than creating them one by one.

The server tracks both visual and text-based changes on a webpage. Your agent gets a diff of the content, so it can see exactly what was added or removed between checks.

Absolutely. The `search_watches` tool is built for this. Your agent can search by URL, title, or tags you've assigned, making it easy to find and manage a specific watch even among hundreds of others.

Your data, specifically the URLs you watch and their content, is processed within a Vinkius ephemeral sandbox. Each operation runs in an isolated V8 Isolate that is destroyed after execution. Nothing is persisted on the server beyond what's needed for the check.

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