ChangeDetection.io MCP. Track exactly what changes on any website.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
ChangeDetection.io MCP Server lets you automate web monitoring and data extraction. Track visual or text updates on any website, manage multiple 'watches,' and get historical snapshots directly through your AI agent.
It's for data analysts and developers who need to know exactly when and how a webpage changes.
What your AI agents can do
Create tag
Creates a new organizational tag for your monitoring projects.
Create watch
Sets up a new monitor for a specified URL.
Delete watch
Removes an existing URL monitor from the system.
You tell the agent which URL to track, and the agent sets up, updates, or deletes the monitoring 'watch' in the system.
The agent fetches two historical snapshots and reports the specific text or visual differences between them.
You apply tags to your watches, allowing you to categorize and manage hundreds of monitoring targets by project or type.
The agent retrieves the complete chronological history of a single URL, allowing you to analyze version trends.
You can search through all your active and inactive watches using criteria like titles or tags.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
ChangeDetection.io MCP Server: 14 Tools for Web Monitoring
These tools let your AI agent create, manage, and query monitors, pull historical snapshots, and pinpoint every change across your tracked web URLs.
019e3876create tag
Creates a new organizational tag for your monitoring projects.
019e3876create watch
Sets up a new monitor for a specified URL.
019e3876delete watch
Removes an existing URL monitor from the system.
019e3876get snapshot
Retrieves the most recent saved version of a specified watch.
019e3876get snapshot diff
Compares two specific snapshots (e.g., 'latest' vs. 'previous') to show what changed.
019e3876get tag
Retrieves the details for a single, specific tag.
019e3876get watch
Fetches all the metadata for a single monitoring watch.
019e3876get watch favicon
Gets the small icon (favicon) used by a specific watch monitor.
019e3876get watch history
Retrieves the complete log of all historical snapshots for a watch.
019e3876import urls
Imports a list of URLs into the monitoring system.
019e3876list tags
Retrieves a full list of all tags currently in use.
019e3876list watches
Lists all active and inactive monitoring watches you've set up.
019e3876search watches
Searches through all your watches using specific criteria.
019e3876update watch
Modifies the settings or URL of an existing watch monitor.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with ChangeDetection.io, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
You gotta hook this server up to your AI client to automate web monitoring and data extraction. You treat the web like a database, setting up monitors and asking questions about changes without ever actually visiting the site.
Create and Manage Monitors
- You can tell the agent which URL to track, and it'll set up, update, or delete the monitoring 'watch' in the system. The agent lets you
create_watchfor a specific URL,update_watchif the site changes, anddelete_watchwhen you're done. You can alsoimport_urlsto dump a bunch of URLs into the system at once. - You can find all your active and inactive monitors using
list_watchesorsearch_watcheswith specific criteria. You can also get a list of all tags withlist_tagsand retrieve details for a specific tag usingget_tag. You cancreate_tagto organize new projects, and you canget_tagto check the details of an existing one. You can also useget_watchto fetch all the metadata for one specific watch.
Compare Web Page Snapshots
- The agent can
get_snapshotto grab the most recent saved version of a watch. Better yet, it canget_snapshot_diffby comparing two specific snapshots—say, 'latest' versus 'previous'—to show you exactly what changed, text or visuals.
Group and Organize Monitors
- You can apply tags to your watches, grouping monitors by project or type. You can
create_tagto set up a new organizational tag, and then you use those tags to manage hundreds of targets, keeping everything neat.
Fetch Historical Data
- The agent can
get_watch_historyto pull the complete log of every historical snapshot for a watch, letting you analyze trends or version changes over time. You can also grab the favicon for a specific watch usingget_watch_favicon.
Search and Filter Monitors
- You can
search_watchesacross all your active and inactive monitors using specific criteria, and you canlist_watchesto see everything you've set up.
How ChangeDetection.io MCP Works
- 1 First, subscribe to the server and provide your ChangeDetection.io API Key and Instance URL.
- 2 Next, ask your AI agent to perform a task—for instance, 'Create a watch for the competitor pricing page.'
- 3 The agent uses the appropriate tool (e.g.,
create_watch) to set up the monitor, and you get a confirmation and the newly assigned UUID.
The bottom line is that your AI agent handles the API calls to set up, check, and compare web data on your behalf.
Who Is ChangeDetection.io MCP For?
This is for data analysts and developers who need to monitor external web assets without manually scraping them. If you track pricing, competitive status, or API documentation, this server saves you from endless manual checks and copy-pasting.
You set up multiple watches on competitor sites to track pricing, product availability, or special offers, getting instant alerts when changes occur.
You monitor key external documentation sites or dependency APIs. The agent alerts you immediately if the structure changes, preventing broken code.
You monitor target landing pages and competitor SERP listings to spot content modifications or structural changes that impact rankings.
What Changes When You Connect
- Monitor Competitors: Use
create_watchto set up dozens of competitor URLs. Your agent tracks price changes or new product launches automatically, so you never miss an update. - Pinpoint Changes: Don't just know that something changed; know what.
get_snapshot_diffcompares two versions and tells you exactly which text or visual element was added or removed. - Audit Full History: Need to see how a page looked six months ago?
get_watch_historypulls the entire record, letting you analyze long-term trends or content decay. - Organize Projects: Group your monitors efficiently. Use
create_tagandlist_tagsto tag watches by project (e.g., 'Q3 Launch' or 'Competitor A'), keeping large-scale monitoring organized. - Quick Check: Don't wait for the scheduled check. Run
get_snapshotto force an immediate check on a watch, getting the absolute latest data right now. - Scale Monitoring: Use
search_watchesandlist_watchesto manage thousands of monitors efficiently, ensuring you always know the status of every URL.
Real-World Use Cases
Tracking Price Changes on an E-commerce Site
A market analyst needs to track a key product's price across three competitor sites. They run create_watch for all three URLs. When a price drops, the agent alerts them, and they use get_snapshot_diff to confirm the exact old and new pricing text.
Monitoring API Documentation Updates
A developer relies on a third-party API's documentation. They set up a watch and run it daily. When the provider updates the API endpoints, the agent alerts them, and they use get_watch_history to compare the old documentation structure against the new one.
Checking for Legal Compliance Changes
An SEO specialist needs to ensure a competitor's landing page maintains specific legal disclaimers. They use create_watch and get_snapshot_diff periodically. The agent flags any removal or modification of the required text.
Managing a Large Portfolio of Assets
A data science team manages hundreds of assets across different projects. They use create_tag to tag watches by 'Project Alpha' and then use list_watches and search_watches to quickly filter and manage the entire portfolio.
The Tradeoffs
Treating all data as a single dump
Asking the agent, 'Tell me everything about my watches.' This returns a huge, unfilterable list of raw metadata without context or grouping.
→
Instead, use list_watches to get the overview, then use search_watches combined with get_tag to filter down to only the watches for 'Project Alpha'.
Guessing which snapshot is current
Asking the agent to compare the 'last' snapshot without specifying the time frame. The agent might compare the wrong version, giving you bad data.
→
Always use get_snapshot first to confirm the 'latest' snapshot UUID, then pass that specific UUID and the 'previous' UUID to get_snapshot_diff.
Manually tracking changes in a spreadsheet
Copying and pasting data from multiple competitor websites into a spreadsheet to manually track price changes or content updates.
→
Use create_watch to monitor the site, and then use get_snapshot_diff to pull the precise, structured changes directly into your workflow.
When It Fits, When It Doesn't
Use this server if your job requires monitoring external, volatile web content—think pricing, legal text, competitor copy, or API documentation. You need to know when and how something changes. Don't use this if you just need to read static, internal data or track user interactions within a single app. For internal data tracking, use a dedicated database connector. If you only need to fetch a single, specific piece of data (like a single tag list), you might only need list_tags, but this server gives you the full lifecycle management (create, delete, search) you need to scale.
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 14 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Manual web monitoring is a time sink.
Right now, if you want to know if a competitor changed their pricing, you open their website. You check the product page. You manually copy the old price into a spreadsheet. You repeat this process for five competitors, five times a day. It’s tedious, error-prone, and you're always behind.
With this MCP server, you set up a watch on the competitor's URL. When they change the price, your agent detects it and reports the difference. You don't open a browser; you just get the specific, actionable data you need.
ChangeDetection.io MCP Server: Get the Data, Not the Website.
You eliminate the need to manually check the site, copy the text, and then manually compare it to a stored version. The agent handles the entire process: checking the URL, pulling the snapshot, and running the `get_snapshot_diff` tool for you.
The result is clean, structured, and immediately actionable data. You stop looking at websites and start making decisions based on the data.
Common Questions About ChangeDetection.io MCP
How do I use the get_snapshot_diff tool? +
The get_snapshot_diff tool requires you to specify two snapshots—usually 'latest' and 'previous.' It then compares the content of those two versions and tells you exactly what changed.
Can I track multiple websites with ChangeDetection.io MCP Server? +
Yes. You use create_watch to set up multiple monitors for different URLs. You can then group them using create_tag to keep your entire monitoring setup organized.
What is the difference between list_watches and search_watches? +
list_watches shows you every single watch you've ever created. search_watches lets you filter that list using specific criteria, helping you find the right monitor faster.
How do I check the full history of a watch? +
Use get_watch_history. This tool pulls the entire timeline of snapshots for a specific watch, letting you analyze trends over time.
How do I update a watch using the ChangeDetection.io MCP Server? +
You use the update_watch tool. This modifies the existing watch's URL or settings without having to delete and recreate the entire monitor.
How do I use the create_watch tool to set up a new monitoring target? +
You use the create_watch tool to establish a new URL monitor. You simply provide the target URL, a title, and optionally, tags. The server then handles the setup and starts tracking changes immediately.
What does the get_watch_history tool provide for a specific monitor? +
The get_watch_history tool retrieves all historical data for a given watch. This lets you analyze trends, see previous versions of the page, and understand how the content has changed over time.
How can I organize and filter my monitors using the create_tag and list_tags tools? +
You manage organization by using create_tag to define categories, and list_tags to see what's available. You then associate tags with your watches to group monitoring projects and filter large sets of data.
Can I see exactly what text changed on a page between the last two checks? +
Yes! Use the get_snapshot_diff tool with the watch UUID. It will return the specific differences between the current state and the previous snapshot.
How do I trigger an immediate recheck of a specific website? +
You can use the get_watch tool and set the recheck parameter to '1'. This forces the server to fetch the latest version of the page immediately.
Can I filter my monitors by tags using the AI? +
Absolutely. When using list_watches, you can provide a tag name to filter the results and only see monitors associated with that specific category.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Arize AI
Automate LLM and ML observability via Arize — monitor models, track telemetry, run evaluations, and analyze data drift directly from any AI agent.
Namsor Alternative
Detect gender, origin, and ethnicity from names, parse full names, and format phone numbers with AI-powered onomastics.
Jina AI (Search Foundation & LLM Grounding)
Power your RAG and search via Jina AI — generate embeddings, rerank documents, read URLs, and perform semantic web search.
You might also like
Kustomer
Manage customer service — list conversations, audit customers, and search timelines.
ZenQuotes API
Access inspirational quotes — audit random and daily quotes via AI.
Feedly
Manage your news aggregation via Feedly — list collections, read streams, and search for feeds directly through your AI agent.