Wayfern
Start building Sign in

Perplexity Computer + Wayfern

Cite the pages that turn bots away.

  • MCP connector, Streamable HTTP
  • OAuth, no client ID
  • Pro, Max and Enterprise
Set it up Create an account

Perplexity Computer searches and reads the open web. Some sources turn automated visitors away with a challenge page, and Computer cannot cite what it cannot read.

Add Wayfern as a connector, and Computer reads those pages in an anti-detect browser, extracts tables with extract_data and searches three engines. It cites the result next to its other sources.

A research memo with numbered citations. Three sources fly in. One shows a challenge page until Wayfern reads it, and its quote fills citation two.

Setup

Add an MCP connector.

Computer runs in Perplexity's cloud and reaches Wayfern over the remote server.

  1. 1

    Open Plugins

    Open Plugins in the sidebar. Older accounts: Customize, Connectors.

  2. 2

    Add a connector

    Click Add custom, Connector, Add MCP connector.

  3. 3

    Enter the server

    Name: Wayfern. Transport: Streamable HTTP. Authentication: OAuth.

    URL

    https://api.wayfern.com/mcp
  4. 4

    Sign in

    Save, then sign in on wayfern.com and click Allow. Perplexity asks for a Client ID and Secret only when a server cannot register clients. Wayfern can, so you need neither.

Route

The connector reads what Computer cannot.

Computer works in Perplexity's cloud and takes remote MCP connectors with OAuth. Wayfern lets a client register itself, so the sign-in needs no Client ID.

Remote MCP OAuth sign-in
Best fit
OAuth with automatic client registration.
MCP + token Authorization header
Not tested
The form has an API Key option. Perplexity does not say which header it sends.
Agent skill SKILL.md
Not tested
Computer can install tools in its own computer. The skill with a token there is not tested.

Example tasks

Research with hard sources

  • 01

    Compare reports

    “Read the summary pages of these three industry reports and compare their market size figures, with a citation for each.”

    scrape_page at 1 credit a page.

  • 02

    Extract a table

    “From the statistics office's release page, extract the monthly figures for 2025 as a table.”

    extract_data bills 1 credit for each uncached source page.

  • 03

    Search three engines

    “Search Google, Bing and DuckDuckGo for independent reviews of the Framework Laptop 16 and group them by verdict.”

    search_web bills 2 credits for each provider page.

  • 04

    Profile a company

    “Get the brand profile of northwind.com: logo, colours, social links and company facts.”

    brand_profile costs 10 credits for a domain.

Tools

What Perplexity Computer 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

Enterprise
An admin adds the connector under Enterprise settings, Permissions, Connectors permissions, Custom connector, Remote. Or the admin turns on Allow members to add custom connectors.
Scheduled Tasks
Computer's Scheduled Tasks run at most once an hour. Each run spends Wayfern credits for its tool calls.

More agents

All AI agents

Connect Perplexity Computer 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