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.

Site Monitoring
Tool call
Sandbox
Result
Call check_website from my assistant.

now

Assistant called check_website
OpenHelm spun up a cloud sandbox
Working through the task…
Evidence-backed result returned
Where shall we steer?
Site Monitoring · live

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.

Remote MCP URL
https://mcp.openhelm.ai/watch/mcp
Local bridge (optional)
npx mcp-remote https://mcp.openhelm.ai/watch/mcp

Tools

What your assistant can call.

Available on https://mcp.openhelm.ai/watch/mcp

check_website

Capture a structured snapshot of a URL now: headlines, key sections, prices, changes-relevant facts.

diff_website

Compare the live page against a prior snapshot; report meaningful differences with quoted evidence.

competitor_brief

One-shot competitive snapshot of a company: positioning, pricing, launches, hiring signals, source-cited.

price_check

Extract current prices, plans and promos from product or pricing URLs into structured JSON.

brand_mentions_sweep

Recent public mentions of a brand or product with source, sentiment and gist.

check_result

Retrieve the finished result of a longer-running sweep or brief.

Get started

Connect in under a minute.

  1. 1

    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.

  2. 2

    Connect your OpenHelm account

    Click Connect and you are sent to 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.

  3. 3

    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.

  4. 4

    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

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.