Wayfern
Start building Sign in

Claude Code + Wayfern

Claude Code reads the live web, and sees it.

  • One command, OAuth sign-in
  • Every tool result reports its credits
  • Playwright scripts can use a Wayfern browser
Set it up Create an account

Claude Code knows your repo. It does not know what the docs page says today, what the error message returns on Google, or how staging looks after a deploy.

With Wayfern as an MCP server, Claude Code calls search_web, scrape_page and capture_screenshot like any other tool. Each call runs in an anti-detect browser and returns markdown, JSON or an image URL, with the credits it cost.

A terminal. The claude mcp add command types in and Claude Code reports the server. A prompt asks to check the staging pricing page. Claude Code calls Wayfern to scrape and capture the page, a screenshot thumbnail appears, and the answer says one plan column is missing.

Setup

Add Wayfern with one command.

Run this in the project where you want the tools, or add --scope user to have them in every project.

  1. 1

    Add the server

    bash

    claude mcp add --transport http wayfern https://api.wayfern.com/mcp
  2. 2

    Sign in

    Start claude, type /mcp, pick wayfern and choose Authenticate. A browser opens on wayfern.com. Sign in and click Allow.

  3. 3

    Check the tools

    Back in Claude Code, /mcp shows wayfern as connected with its tools. Ask for a page and watch the tool calls.

    prompt

    > Read https://docs.stripe.com/api/charges/create and list every required parameter.

Other ways to connect

  • With a token instead of OAuth

    For CI and containers with no browser. Create a token with the mcp scope on the Tokens page.

    bash

    claude mcp add --transport http wayfern https://api.wayfern.com/mcp \
  --header "Authorization: Bearer $WAYFERN_API_TOKEN"

  • As an agent skill

    The skill tells Claude Code how to call the REST API with curl. It needs WAYFERN_API_TOKEN in the environment.

    bash

    mkdir -p ~/.claude/skills/wayfern
curl -fsSL https://wayfern.com/skills/wayfern/SKILL.md -o ~/.claude/skills/wayfern/SKILL.md

Route

Claude Code takes the remote server.

Claude Code supports remote HTTP servers with OAuth. One sign-in covers every tool, and no token sits in a config file.

Remote MCP OAuth sign-in
Best fit
claude mcp add and /mcp sign you in on wayfern.com.
MCP + token Authorization header
Works
Pass --header with a wf_ token. Good for CI.
Agent skill SKILL.md
Works
Put SKILL.md in ~/.claude/skills/wayfern. Claude Code calls the REST API with curl.
REST API api.wayfern.com/api/v1
Works
Claude Code can write code that calls api.wayfern.com/api/v1 directly.
Browser API Playwright over CDP
Works
Claude Code can write Playwright code that connects to a Wayfern browser over CDP.

Example tasks

Jobs for the terminal

  • 01

    Read current docs

    “Read the v5 migration guide of the router we use and list each change that breaks our code in src/routes.”

    scrape_page returns the page as markdown for 1 credit.

  • 02

    Check a deploy

    “Capture the pricing page on staging, full page, and tell me if the plan table shows four columns.”

    capture_screenshot returns an image URL for 5 credits.

  • 03

    Search an error

    “Search Google and Bing for this stack trace and summarise the fixes that people confirm.”

    search_web bills 2 credits for each provider page.

  • 04

    Pull docs into the repo

    “Crawl the API reference of our payment provider, 40 pages at most, and save each page as markdown under docs/vendor.”

    crawl_site bills 1 credit for each page it scrapes.

Tools

What Claude Code 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

Credits
Each tool result has credits_charged. list_search_engines, crawl_status and get_usage are free.
Scope
Without --scope, the server is in this project only. --scope user adds it to every project on your computer.

More agents

All AI agents

Connect Claude Code in a minute.

Sign in once and the tools appear. Tool calls use the credits of your Wayfern plan, at the same rates as the API.

Create an account Read the guides