How to Use the ChangeDetection.io MCP in Google ADK

Q: How does the ChangeDetection.io MCP Server work with Google ADK?

You instantiate an McpToolset with your Vinkius server URL and pass it to your LlmAgent. The ADK framework handles the connection, and your Gemini agent can immediately start using tools like createwatch and listtags.

Q: Can I filter which ChangeDetection.io tools my Google ADK agent can access?

Yes. When you set up the McpToolset, you can pass an optional toolnames filter. This lets you expose only a subset of tools, like getsnapshot and getwatchhistory, if you want to create a read-only agent.

Q: How can my agent compare two versions of a site with ChangeDetection.io and Google ADK?

The getsnapshotdiff tool is designed for this. Your agent can request the difference between the 'latest' snapshot and the 'previous' one. It gets back a clear diff that it can then analyze or summarize.

Connect your Google ADK agents to the live web. Let Gemini models reason over real-time website changes from ChangeDetection.io.

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 Google ADK

Create your Vinkius account to connect ChangeDetection.io to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect Google Cloud to the outside world

Your Gemini agent, running on Google Cloud, can now monitor external websites. Use `import_urls` to feed it a list of competitor sites or regulatory pages straight from a BigQuery table. Your agent can then automatically `create_watch` for each one. This is how you bridge your internal Google Cloud data with what's happening outside your firewall. The agent acts as the go-between, pulling real-world data into your enterprise ecosystem.

Use long-context reasoning on web data

This MCP Server is a perfect match for Gemini's long-context capabilities. Your agent can pull a site's entire change log using `get_watch_history` and feed it into a model with a million-token context window. From there, your agent can summarize months of changes, identify trends, or find a specific update using `get_snapshot_diff`. You're not just checking for changes; you're performing large-scale analysis on web data using Google's most powerful models.

Automate monitoring with a Gemini agent

Your Google ADK agent can do more than just read data; it can manage the entire monitoring process. It has the tools to `create_tag` to organize watches, `update_watch` to change check frequency, or `delete_watch` to clean up old tasks. This gives you a fully automated system for web intelligence gathering, controlled by an agent running in your Google Cloud environment. It's a hands-off way to keep tabs on the websites that matter to your business.

Setup guide

Set up ChangeDetection.io MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with ChangeDetection.io tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="ChangeDetection.io_agent",
    model="gemini-2.0-flash",
    instruction="You have access to ChangeDetection.io tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

You instantiate an `McpToolset` with your Vinkius server URL and pass it to your `LlmAgent`. The ADK framework handles the connection, and your Gemini agent can immediately start using tools like `create_watch` and `list_tags`.

Yes. When you set up the `McpToolset`, you can pass an optional `tool_names` filter. This lets you expose only a subset of tools, like `get_snapshot` and `get_watch_history`, if you want to create a read-only agent.

Definitely. A common pattern is to have your agent query a list of URLs from a BigQuery table, then loop through that list and use the `create_watch` or `import_urls` tool for each one. It's a great way to sync your monitoring with your existing data.

The `get_snapshot_diff` tool is designed for this. Your agent can request the difference between the 'latest' snapshot and the 'previous' one. It gets back a clear diff that it can then analyze or summarize.

The server handles the URLs you are watching and the text content of those pages. All operations on this data are executed within Vinkius's zero-trust infrastructure. Your requests run in sandboxed, single-use environments that are torn down after they're done.

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