ChatGPT + Wayfern

ChatGPT answers from the page, not from memory.

  • Remote MCP with OAuth
  • ChatGPT asks before each tool call
  • Credits come from your Wayfern balance

ChatGPT browses, but sites that block bots return a challenge page, and the answer comes from memory.

With Wayfern as a plugin, ChatGPT calls Wayfern tools. Each tool runs in an anti-detect browser and returns markdown, JSON or an image URL. ChatGPT shows each call before it runs.

A ChatGPT chat. The user types @ and picks the Wayfern plugin, then asks for a price table. ChatGPT asks to run a Wayfern tool, the user allows it, and a table of three prices comes back.

Setup

Add Wayfern as a custom MCP plugin.

Do this one time, in ChatGPT on the web.

  1. 1

    Open Plugins

    Go to chatgpt.com/plugins. Click the plus button, then Add custom MCP server.

  2. 2

    Enter the server

    Name it Wayfern. Under Connection, paste the server URL. Set Authentication to OAuth.

    URL

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

    Create the plugin

    Read the risk warning. Click I understand and want to continue, then Create as a plugin.

  4. 4

    Install and sign in

    Install the plugin from your personal plugins. ChatGPT opens wayfern.com. Sign in and click Allow.

  5. 5

    Mention it in a chat

    Type @ and pick Wayfern, then ask.

    prompt

    @Wayfern Read the pricing pages of Linear, Height and Plane. Make a table of the price per seat for each plan.

Route

ChatGPT reaches Wayfern over the remote server.

ChatGPT connects only to public remote MCP servers. It cannot send a custom header or run commands on your computer, so OAuth is the one route.

Remote MCP OAuth sign-in
Best fit
OAuth sign-in on wayfern.com. ChatGPT asks you to confirm tool calls.
MCP + token Authorization header
No
ChatGPT has no field for a custom Authorization header.
Agent skill SKILL.md
No
A chat has no shell to run curl.
REST API api.wayfern.com/api/v1
No
ChatGPT does not call REST APIs on its own.

Example tasks

Questions for a chat

  • 01

    Compare prices

    “Read the pricing pages of these four tools and make a table of the monthly price for 10 seats.”

    scrape_page reads each page for 1 credit.

  • 02

    Brand colours

    “Get the brand colours and fonts of stripe.com and give them to me as CSS variables.”

    brand_profile costs 10 credits for a domain.

  • 03

    Fresh search

    “Search Google, Bing and DuckDuckGo for reviews of the Framework Laptop 16 from this month. Group them by verdict.”

    search_web with three engines and a date range.

  • 04

    See the page

    “Take a full-page screenshot of our landing page in dark mode and tell me what looks broken.”

    capture_screenshot returns an image URL that ChatGPT can open.

Tools

What ChatGPT 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

Plans
OpenAI lists full custom MCP support for Business, Enterprise and Edu workspaces. Check your plan before you set it up.
Credits
Each tool call uses credits from your Wayfern balance at the REST API rates. get_usage shows your balance.