Wayfern
Start building Sign in

Cue + Wayfern

A connector to try when Cue offers one.

  • No documented MCP connector
  • A remote server to try
  • Cue is invite only
Set it up Create an account

A Cue agent has its own email address, phone number and computer, and it keeps working after you log off. Cue does not document a way to add your own MCP server.

Cue runs on the same base as Manus, which adds MCP servers by URL. If your Cue agent shows that option, add Wayfern, and it can read public pages, search three engines and capture screenshots for household research.

Note:Cue does not document custom MCP connectors. Every step on this page is a test.

A Cue agent's settings panel. A connector form fills in with the Wayfern URL, then a stamp lands on it that reads To try. Below it, a test question about boiler prices waits.

Setup

What to try.

These steps are a test. Stop at the first step that your Cue agent does not offer.

  1. 1

    Look for a connector

    Open your Cue agent's settings and look for a custom MCP or connector option. Cue does not document one.

  2. 2

    Enter the server

    If it asks for a URL, paste this one.

    URL

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

    Sign in

    If it offers OAuth, sign in on wayfern.com and click Allow. If it asks for a Bearer token, create one with the mcp scope on the Tokens page.

  4. 4

    Limit it

    Give the connector only to the agent that does the research.

Route

Try the remote server first.

Manus, which Cue is built on, adds MCP servers by URL. If Cue offers the same, the remote server needs no install on the Cue computer.

Remote MCP OAuth sign-in
Best fit
The route to try: the server URL and an OAuth sign-in. Cue does not document it.
MCP + token Authorization header
Not tested
A wf_ token in a Bearer field, if Cue shows one.
Agent skill SKILL.md
Not tested
Cue does not document a shell on its computers.
REST API api.wayfern.com/api/v1
Not tested
If Cue gets a custom API option, the REST API takes a token.

Example tasks

Household research

  • 01

    Compare service prices

    “Read the price pages of three local boiler service firms and tell me the cheapest for a yearly service.”

    scrape_page at 1 credit a page.

  • 02

    List school holidays

    “Read the school district's calendar page and list the holidays for the rest of the year.”

    extract_data bills 1 credit for each uncached source page.

  • 03

    Read product reviews

    “Search for reviews of the three robot vacuums on my list and summarise each in two lines.”

    search_web bills 2 credits for each provider page.

  • 04

    Save a listing

    “Capture the rental listing at this link and save the image with my notes.”

    capture_screenshot returns a downloadable image URL for 5 credits.

Tools

What Cue 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

Access
Cue is invite only. Get a code from the Agents tab in the Manus sidebar or by email. Apps exist for Mac and Android.
Messengers
Cue agents talk on iMessage, Telegram, LINE and Slack.

More agents

All AI agents

Connect Cue 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