Grok Bot + Wayfern

A Bot that checks the page while you work.

  • Remote HTTPS MCP server
  • Each teammate signs in
  • Routines down to 5 minutes

A Grok Bot routine wakes up on a schedule and does a job. When the job needs a page from a site that blocks bots, the routine gets a challenge page.

With Wayfern as a remote MCP server, the routine scrapes the page, extracts the fields or captures a screenshot, and reports what changed. Each teammate signs in with their own Wayfern account.

A row of checks, one every 15 minutes. At 10:00 and 10:15 the venue page shows no Buy button. At 10:30 it does, and the Bot posts a message with the link and a screenshot.

Setup

Give the Bot an MCP server.

xAI documents MCP servers for Team Bots, in the Bot's Setup.

  1. 1

    Open the Bot's Setup

    Open the Bot's info pane, then Setup.

  2. 2

    Add a remote server

    Add a custom MCP server of the type Remote HTTPS, with this URL.

    URL

    https://api.wayfern.com/mcp
  3. 3

    Sign in

    Each teammate signs in on wayfern.com with OAuth the first time the Bot uses Wayfern for them.

  4. 4

    Give it a routine

    prompt

    Every 15 minutes, read the venue's page for the 14 November concert with Wayfern. Tell me when tickets go on sale.

Route

The Bot calls Wayfern from the cloud.

Grok Bot reaches remote MCP servers from Cursor's servers, so the public URL works. Each person signs in with their own Wayfern account and pays from their own balance.

Remote MCP OAuth sign-in
Best fit
A Remote HTTPS server with OAuth.
MCP + token Authorization header
Not tested
xAI does not document a header field for a remote server.
Agent skill SKILL.md
Not tested
A skill on the Bot's cloud computer with a token is not documented.
REST API api.wayfern.com/api/v1
In part
From the Bot's cloud computer with a token in Secrets. xAI does not say if personal secrets reach the shell.

Example tasks

Watches on a schedule

  • 01

    Catch a ticket sale

    “Every 15 minutes, read the venue's page for the 14 November concert. Tell me when the Buy button shows.”

    scrape_page at 1 credit a check: 96 credits a day.

  • 02

    Read new job posts

    “Every weekday at 8:00, search Google for senior product designer jobs in Berlin from the last day. Send me the new ones.”

    search_web with a date range bills 2 credits for each provider page.

  • 03

    Wait for a price drop

    “Every hour, read the price of the Sony A7 IV on these two shop pages. Tell me when it drops under 1,800 EUR.”

    extract_data bills 1 credit for each uncached source page.

  • 04

    Check a status page

    “Each morning, capture our status page and tell me if a component is not green.”

    capture_screenshot costs 5 credits a capture.

Tools

What Grok Bot can call

The same tools on every route, at the REST API rates. Every result reports credits_charged.

All tool inputs
  • scrape_page Fetch one page through an anti-detect browser and return clean markdown, HTML, links and metadata. The screenshot, pdf and json formats add +4 credits (once); summary adds +2. 1 credit / page
  • extract_data Extract structured data from one or more pages with a prompt and an optional JSON Schema. Re-running over pages already fetched is free. 1 credit / uncached source page
  • map_site List a site's URLs from its sitemaps and page links. 2 credits / 10 URLs
  • capture_screenshot Capture a clean image of a page: cookie banners and ads removed, lazy images loaded, tall pages captured end to end. Returns a short-lived download URL and an artifact key, not image bytes. Slices of a full page cost nothing extra; a fail_if_contains match is not charged. 5 credits / capture
  • brand_profile Identity, colours, logos, social links and company metadata for a domain. 10 credits / profile
  • site_styleguide Colours, typography, spacing, radii, shadows and the design tokens a site declares. 10 credits / site
  • site_fonts Font families, where each is served from, available weights, file formats and where they are used. 5 credits / site
  • crawl_site Start a bounded multi-page crawl. Returns a job id immediately and charges nothing up front; pages are billed as the crawl runs. 1 credit / successful page
  • crawl_status Poll a crawl started with crawl_site and read a page of its results. The pages were billed as they were crawled. Free
  • search_web Search Google, Bing, and DuckDuckGo. Returns ranked results, ads, provider failures, pagination, and related queries. 2 credits / provider page
  • list_search_engines List live provider ids and labels. Free

Good to know

Personal Bots
xAI documents the Setup screen for Team Bots. A Cursor forum reply says that a personal Bot adds a server when you ask in chat; xAI's docs do not confirm it.
Approvals
Grok Bot offers Allow once, Always allow and Deny. A request in the background expires after about 10 minutes.
Plans
Grok Bot needs Cursor Pro, Pro+, Ultra or Teams, a linked SuperGrok, Plus, Heavy or X Premium+ plan, or Grok Business.