How to Use the ChangeDetection.io MCP in CrewAI

Q: How do I configure a CrewAI agent to use ChangeDetection.io?

Pass your Vinkius HTTP endpoint URL directly into the mcps parameter of your CrewAI Agent definition. This automatically exposes tools like listwatches and getsnapshot to that specific agent via the MCP protocol.

Q: Can CrewAI run sequential workflows for ChangeDetection.io monitoring?

Yes, CrewAI executes tasks sequentially where Agent A runs listwatches, Agent B fetches updates via getsnapshot, and Agent C processes the changes.

Q: How do I limit which ChangeDetection.io tools a CrewAI agent can access?

Use MCPServerHTTP from crewai.mcp and define a toolfilter. This restricts a junior agent to getwatch while reserving deletewatch for your manager agent.

Q: Can a CrewAI analyst agent compare page versions on ChangeDetection.io?

Yes, the analyst agent calls getsnapshotdiff using previous and latest parameters. CrewAI's shared memory allows the analyst to pass this text difference to a writer agent for report generation.

Deploy a team of autonomous agents using CrewAI and the ChangeDetection.io MCP Server to track and analyze web changes.

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 CrewAI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Competitor Intelligence with CrewAI

This ChangeDetection.io MCP Server allows a CrewAI research agent to autonomously manage your tracking targets. The research agent uses `import_urls` to add new competitor pages to your watchlist. A separate analyst agent then calls `get_snapshot_diff` to extract text modifications. This division of labor keeps your data collection decoupled from your analytical reasoning.

Autonomous Watch Auditing and Cleanup

This server exposes `list_watches` and `get_watch_history` to audit your active monitoring footprint. A CrewAI auditor agent scans your list to find stagnant or broken watches. The auditor agent coordinates with a supervisor agent to execute `delete_watch` on dead links. This keeps your monitoring dashboard clean without any human intervention.

Hierarchical Site Classification

This toolset uses `create_tag` and `get_tag` to organize website targets. Your CrewAI classification agent reads page content and decides how to tag each source. The agent then executes `update_watch` to apply the tag. Other agents in the crew read these tags using `list_tags` to prioritize their daily analysis reports.

Setup guide

Set up ChangeDetection.io MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke ChangeDetection.io tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="ChangeDetection.io Analyst",
    goal="Access and analyze ChangeDetection.io data via MCP.",
    backstory="Expert analyst with direct ChangeDetection.io access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent ChangeDetection.io transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="ChangeDetection.io Analyst",
        goal="Access and analyze ChangeDetection.io data via MCP.",
        backstory="Expert analyst with direct ChangeDetection.io access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent ChangeDetection.io transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass your Vinkius HTTP endpoint URL directly into the `mcps` parameter of your CrewAI Agent definition. This automatically exposes tools like `list_watches` and `get_snapshot` to that specific agent via the MCP protocol.

Yes, CrewAI executes tasks sequentially where Agent A runs `list_watches`, Agent B fetches updates via `get_snapshot`, and Agent C processes the changes.

Use `MCPServerHTTP` from `crewai.mcp` and define a `tool_filter`. This restricts a junior agent to `get_watch` while reserving `delete_watch` for your manager agent.

Yes, the analyst agent calls `get_snapshot_diff` using previous and latest parameters. CrewAI's shared memory allows the analyst to pass this text difference to a writer agent for report generation.

Your monitored URL lists and watch settings are protected by the encrypted Vinkius transport layer. The CrewAI agents interact with the MCP Server through a secure endpoint, ensuring no raw HTML snapshots leak outside your execution environment.

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