Wayfern
Start building Sign in

Claude Cowork + Wayfern

Cowork writes the file. Wayfern reads the web.

  • Custom connector with OAuth
  • Claude Pro, Max, Team, Enterprise
  • Results go into your folders
Set it up Create an account

Cowork works with the files in your trusted folders: a sheet of competitors, a folder of reports. The data for those files is often on sites that block automated visits.

With Wayfern as a connector, Cowork scrapes the pages, extracts the fields and searches three engines. Then it writes the result into a CSV, a document or a slide in your folder.

Claude Desktop in Cowork. A list of competitor URLs is on the left. Wayfern scrape calls run one by one, and rows fill a pricing.csv file in the trusted folder on the right.

Setup

Connect Wayfern, then trust a folder.

Cowork uses the connectors of your Claude account. It does not read Claude Code's settings.

  1. 1

    Open Connectors

    In Claude Desktop, open Customize, Connectors. Click Add custom connector.

  2. 2

    Enter the server

    Name it Wayfern. Paste the URL and set Authentication to Sign in now.

    URL

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

    Connect

    Click Add, then Connect. Sign in on wayfern.com and click Allow.

  4. 4

    Trust the folders

    Connect the folders that the work needs, for example ~/Research. They show under Trusted folders in Settings.

  5. 5

    Give it the job

    prompt

    For each URL in competitors.txt, read the pricing page with Wayfern. Write plan names, prices and seat limits to pricing.csv.

Other ways to connect

  • With a token header

    Organizations with request headers (a beta) can choose No sign-in and send a wf_ token with the mcp scope.

    prompt

    Authorization: Bearer wf_...

Route

The connector brings the web into Cowork.

Cowork uses the custom connectors of your Claude account. Wayfern's remote server signs in with OAuth, so Cowork needs no install and no token.

Remote MCP OAuth sign-in
Best fit
A custom connector with OAuth, on every paid Claude plan.
MCP + token Authorization header
In part
Only for organizations with request headers, a beta.
Agent skill SKILL.md
Not tested
Anthropic does not say if Cowork's sandbox can reach api.wayfern.com with your token.

Example tasks

Desk research into files

  • 01

    Build a pricing sheet

    “For each URL in competitors.txt, read the pricing page and write plan names, prices and seat limits to pricing.csv.”

    scrape_page at 1 credit a page. Cowork writes the CSV.

  • 02

    Collect open roles

    “Extract the title, team and location of every open role on these three careers pages into roles.xlsx.”

    extract_data bills 1 credit for each uncached source page.

  • 03

    List a docs site

    “List every URL under docs.example.com/guides and save the list as guides.txt.”

    map_site bills 2 credits for each 10 URLs.

  • 04

    Log the press coverage

    “Search Google for articles about our launch from the last 30 days. Save the title, outlet, date and link of each to coverage.md.”

    search_web bills 2 credits for each provider page.

Tools

What Claude Cowork 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

Approval modes
Cowork has Manual, Auto and Skip. Most Wayfern tools only read, but each call that fetches a page spends credits.
Credits
Each tool result has credits_charged. get_usage shows your balance and is free.

More agents

All AI agents

Connect Claude Cowork 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