How to Use the ChangeDetection.io MCP in Pydantic AI

Q: How do I connect the ChangeDetection.io server to my Pydantic AI agent?

It's simple. You create an MCPToolset instance, passing in your Vinkius endpoint URL. Then you add that toolset to the list of tools when you initialize your Agent.

Q: What happens if the ChangeDetection.io API changes unexpectedly?

Your Pydantic AI agent will fail loudly with a ValidationError. This is a core benefit—it prevents your agent from working with malformed or unexpected data, protecting the rest of your application from silent errors.

Q: How does my agent get the actual content changes from ChangeDetection.io in Pydantic AI?

Your agent uses the getsnapshotdiff tool. The response, like all others, is parsed into a Pydantic model, giving you a clean, typed object that contains the difference between two checks. You can trust its structure every time.

Get type-safe website change alerts in Python. Your Pydantic AI agent gets validated data from ChangeDetection.io, so you can trust every response.

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 Pydantic AI

Create your Vinkius account to connect ChangeDetection.io to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build agents that don't silently fail

This is how you build reliable agents. When your Pydantic AI agent calls `get_watch` or `list_watches`, the JSON response from the server is automatically parsed and validated against a Pydantic model at runtime. If the server ever returns an unexpected field or the wrong data type, your code raises a `ValidationError` immediately. No more chasing down bugs caused by corrupted API data. You get correctness, guaranteed.

Model-agnostic monitoring with this MCP Server

Your Pydantic AI agent can `create_watch` on a URL and then use `get_snapshot_diff` to see what changed, all with guaranteed data structures. The tool's output is just as reliable as its input. Because Pydantic AI is model-agnostic, you can swap between OpenAI, Anthropic, or a local LLM without rewriting your monitoring logic. The MCP Server provides the tools; Pydantic AI provides the reliable data contract that makes them safe to use.

Manage monitoring tasks with precision

Your agent can manage its own workload with predictable, structured tools. It can use `create_tag` to organize a set of URLs, then `search_watches` to find a specific one to modify. You know the exact structure of the data at every step. Every action, from `update_watch` to `delete_watch`, works with the same type-safe guarantee. You're not just telling an agent what to do; you're giving it a structured, predictable toolset to work with.

Setup guide

Set up ChangeDetection.io MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "changedetectionio-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to ChangeDetection.io tools.",
)

result = await agent.run("List recent ChangeDetection.io transactions")
print(result.output)

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 Pydantic AI

It's simple. You create an `MCPToolset` instance, passing in your Vinkius endpoint URL. Then you add that toolset to the list of tools when you initialize your `Agent`.

Your Pydantic AI agent will fail loudly with a `ValidationError`. This is a core benefit—it prevents your agent from working with malformed or unexpected data, protecting the rest of your application from silent errors.

Yes, that's the point of Pydantic AI. The framework is model-agnostic, so whether you're using GPT-4, Claude 3, or a local model, your agent can call tools like `create_watch` and `get_watch_history` in the exact same way.

Your agent uses the `get_snapshot_diff` tool. The response, like all others, is parsed into a Pydantic model, giving you a clean, typed object that contains the difference between two checks. You can trust its structure every time.

The server processes the website URLs you provide and their text content. Every tool call is handled by Vinkius in a sandboxed execution environment. The environment is created for your request and immediately destroyed afterward, ensuring none of your data is left behind.

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