How to Use the ChangeDetection.io MCP in AutoGen

Q: How do AutoGen agents collaborate on ChangeDetection.io alerts?

One agent fetches the latest change using getsnapshotdiff and shares it in the group chat. Other specialized agents then analyze the diff from safety and marketing perspectives before taking action.

Q: Can AutoGen agents dynamically add new targets to ChangeDetection.io?

Yes, your planning agent can invoke createwatch when it identifies a missing data source. The agent can then use createtag to group the new monitor based on the conversation context.

Q: How do agents prevent importing duplicate monitoring targets?

Your agents use searchwatches to check if a URL is already being tracked before attempting to add it. This keeps your active watch list clean and avoids redundant API calls.

Run multi-agent debates in AutoGen to verify and respond to live website changes via this 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 AutoGen

Create your Vinkius account to connect ChangeDetection.io to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Verification of Web Diffs

The `get_snapshot_diff` tool delivers raw HTML and text changes directly to your AutoGen agent group for collaborative analysis. A security agent can inspect the diff for suspicious script changes while a copywriter agent evaluates the positioning updates. They debate the implications of the change before agreeing on an alert. It's a reliable way to prevent false alarms because the agents must reach consensus on whether the diff is actually important before notifying you.

Collaborative Watch Management via MCP Server

The `create_watch` tool allows your AutoGen coordinator to deploy new URL monitors after multiple agents debate which sources are trustworthy. If one agent proposes tracking a new site, a verification agent checks its reputation before executing the tool. Once approved, the coordinator uses `create_tag` to label the watch under the correct category. This keeps your monitoring footprint clean and organized by consensus.

Automated Bulk Import and Tagging

The `import_urls` tool lets your AutoGen agents ingest lists of target sites in bulk during automated discovery phases. A coordinator agent parses raw lists, while a categorization agent determines the tags to apply. Running `list_watches` through the MCP Server allows the coordinator to verify duplicates before importing. Your database remains clutter-free without requiring manual human cleanup.

Setup guide

Set up ChangeDetection.io MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes ChangeDetection.io tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="ChangeDetection.io_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent ChangeDetection.io data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="ChangeDetection.io_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent ChangeDetection.io data")
    print(result.messages[-1].content)

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 AutoGen

One agent fetches the latest change using `get_snapshot_diff` and shares it in the group chat. Other specialized agents then analyze the diff from safety and marketing perspectives before taking action.

Yes, your planning agent can invoke `create_watch` when it identifies a missing data source. The agent can then use `create_tag` to group the new monitor based on the conversation context.

If one agent wants to modify a watch and another objects, they debate using the output of `get_watch`. They only trigger `update_watch` once they reach a consensus on the new parameters.

Your agents use `search_watches` to check if a URL is already being tracked before attempting to add it. This keeps your active watch list clean and avoids redundant API calls.

Your keys are held inside the secure Vinkius V8 isolate sandbox. AutoGen agents only interact with the MCP Server tools, never seeing the underlying credentials or raw database configurations.

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