MCP server · Site & competitor monitoring
Website change monitoring your agent can actually reason about.
Pixel-diff monitors page you at 3am because a cookie banner moved. OpenHelm captures structured snapshots, diffs meaning rather than markup, and reports "no meaningful change" honestly. Ask for a competitor brief, a price check, or a brand-mention sweep in plain English.
What it does
The monitoring server turns page-watching into structured facts. check_website captures what a page actually says, headlines, sections, prices and plans, as a snapshot your assistant can store; diff_website fetches the live page and reports meaningful differences against a prior snapshot, each with quoted evidence, and says "no meaningful change" when that is the truth. Around that core sit one-shot competitor briefs (positioning, pricing, launches, hiring signals, all source-cited), structured price/plan extraction, and brand-mention sweeps across the public web.
Every tool is read-only and fails explicitly when a page is unreachable or requires authentication, it never substitutes cached or guessed content. For always-on monitoring on a schedule, with alerts only when something meaningful changes, adopt the Site & Competitor Monitoring strategy in the OpenHelm app; these tools are the one-shot actions.
Endpoint
Add this URL to your MCP client.
https://mcp.openhelm.ai/watch/mcpnpx mcp-remote https://mcp.openhelm.ai/watch/mcpTools
What your assistant can call.
Available on https://mcp.openhelm.ai/watch/mcp
check_websiteCapture a structured snapshot of a URL now: headlines, key sections, prices, changes-relevant facts.
diff_websiteCompare the live page against a prior snapshot; report meaningful differences with quoted evidence.
competitor_briefOne-shot competitive snapshot of a company: positioning, pricing, launches, hiring signals, source-cited.
price_checkExtract current prices, plans and promos from product or pricing URLs into structured JSON.
brand_mentions_sweepRecent public mentions of a brand or product with source, sentiment and gist.
check_resultRetrieve the finished result of a longer-running sweep or brief.
Get started
Connect in under a minute.
Add the remote server
In ChatGPT, Claude, Cursor or any MCP client, add a remote connector pointing at https://mcp.openhelm.ai/watch/mcp. No install, no terminal, no Node setup. For clients that need a local bridge, run npx mcp-remote https://mcp.openhelm.ai/watch/mcp.
Connect your OpenHelm account
Click Connect and you are sent to www.app.openhelm.ai/connect to authorise via OAuth 2.1. Your encrypted OpenHelm API key is wrapped in a signed token, the server itself stores no secrets.
Add a card to start the trial
New accounts add a card to activate a 14-day free trial (you are not billed during the trial). This keeps the shared cloud compute protected from multi-account abuse.
Run tasks from your assistant
Ask your assistant in plain English. It calls the right tool, OpenHelm spins up an isolated cloud browser sandbox, and returns evidence-backed structured results, polling check_result for longer runs.
Want scheduled watches with email or webhook alerts and an evidence-backed change log? The Site & Competitor Monitoring strategy runs the whole pipeline for you.
Set up always-on monitoring→Common questions about the Site Monitoring server
How is this different from Visualping or Distill?
Pixel and DOM diff tools alert on visual change, including banners, rotating testimonials and layout tweaks. OpenHelm reads the page like an analyst: it reports what changed in meaning (a price, a plan, a claim, a new page) with quoted evidence, and stays silent when nothing meaningful happened. And because it is an MCP server, the result lands in your assistant as structured data you can act on, not an email screenshot.
Do I need to install anything?
No. OpenHelm MCP servers are remote, Streamable-HTTP servers. You add a URL as a remote connector in ChatGPT, Claude, Cursor or another MCP client. Clients without native remote support can use the lightweight npx mcp-remote bridge.
Where does the work actually run?
Not on the MCP endpoint. When a tool is called, OpenHelm starts an asynchronous agent run in an isolated E2B cloud sandbox that drives a real browser and reads official sources. The MCP layer is stateless: it holds no database and stores no secrets.
What happens with long-running tasks?
The server uses a bounded-wait pattern of about 75 seconds. Fast tasks return their structured result in one turn. Slower tasks return a task_id and your assistant calls check_result a moment later to retrieve the finished output, so connections never time out mid-run.
How is it billed?
Connecting requires an OpenHelm account with a card on file, which starts a 14-day free trial. You are not charged during the trial. After that, usage runs on your OpenHelm plan.
More servers
Explore the rest of the OpenHelm MCP suite.
Developers, engineering teams & power users
General-Purpose
Spin up a virtual computer for any custom task, browse, run code, read data, and return structured results.
Investment analysts, VCs & corporate strategy teams
Deep Research
A virtual research environment that reads SEC filings, earnings prints, and live market data, grounded in official sources.
Growth marketers, content directors & SEO specialists
SEO & GEO
A virtual SEO environment: audit rankings, draft content, and measure AI engine citations of your brand.
Founders, sales & ops teams, and AI agents
Email Outreach
A virtual inbox your agent controls, send, monitor replies, and run the whole conversation to completion.
Engineering teams, indie developers & AI coding agents
Dev Changes
A virtual coding environment: clone the repo, make the change, run tests, and open a PR.
Sales, support & operations teams · soon
Phone Reach-Out
A virtual phone your agent uses to call, converse, and act on the outcome, coming soon.
Sales, support & operations teams · soon
WhatsApp Reach-Out
A virtual WhatsApp inbox your agent uses to message, handle replies, and achieve the goal, coming soon.
Operations, procurement & personal assistants · soon
Online Buying
A virtual shopper that sources products, compares options, and checks out within your guardrails, coming soon.
Want it run for you instead?
The MCP servers put the tools in your assistant. If you'd rather we run the whole workflow as a managed service, book a 20-minute call and we'll scope it.