Wayfern
Start building Sign in

OpenClaw + Wayfern

Text a question. Get the page's answer.

  • ~/.openclaw/openclaw.json
  • OAuth or a token header
  • Replies in your chat app
Set it up Create an account

OpenClaw lives in the chat apps you already use. You ask it if a shop has stock or what a venue posted today, and the answer is on a site that blocks bots.

With Wayfern on the gateway, OpenClaw scrapes the page, searches three engines or captures a screenshot, and replies in the same chat. Automations run the same checks on a schedule.

A phone with a chat. The user asks if a bike is in stock. OpenClaw answers that it is checking the shop with Wayfern, then replies with the stock and a small screenshot of the product page.

Setup

Add Wayfern to the gateway.

Do this on the machine that runs the OpenClaw gateway.

  1. 1

    Add the server

    Set transport yourself. Without it, OpenClaw uses SSE.

    ~/.openclaw/openclaw.json

    {
  mcp: {
    servers: {
      wayfern: {
        url: "https://api.wayfern.com/mcp",
        transport: "streamable-http",
        auth: "oauth",
      },
    },
  },
}
  2. 2

    Sign in

    A browser opens on wayfern.com. Sign in and click Allow.

    bash

    openclaw mcp login wayfern
  3. 3

    Check and load it

    bash

    openclaw mcp doctor --probe
openclaw mcp reload
  4. 4

    Text it

    prompt

    What does the bakery's site say about opening hours on public holidays?

Other ways to connect

  • With a token

    Put WAYFERN_API_TOKEN=wf_... in ~/.openclaw/.env, with a token that has the mcp scope. OpenClaw ignores a fixed Authorization header while auth is oauth, so use one or the other.

    ~/.openclaw/openclaw.json

    {
  mcp: {
    servers: {
      wayfern: {
        url: "https://api.wayfern.com/mcp",
        transport: "streamable-http",
        headers: { Authorization: "Bearer ${WAYFERN_API_TOKEN}" },
      },
    },
  },
}

  • As an agent skill

    Skills in ~/.openclaw/skills reach every agent on the gateway host, and OpenClaw reloads them when a SKILL.md changes. The skill needs WAYFERN_API_TOKEN in the environment.

    bash

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

Route

The gateway keeps the sign-in.

The gateway holds the MCP session and the tokens for every chat. Each question is a few tool calls, and each result reports its credits.

Remote MCP OAuth sign-in
Best fit
openclaw mcp login wayfern on the gateway host.
MCP + token Authorization header
Works
A header with ${WAYFERN_API_TOKEN} from ~/.openclaw/.env.
Agent skill SKILL.md
Works
Put SKILL.md in ~/.openclaw/skills/wayfern. The exec tool runs curl, with exec approvals.

Example tasks

Questions you text

  • 01

    Check stock

    “Is the Trek Marlin 7 in size M in stock at the bike shop's online store?”

    scrape_page at 1 credit.

  • 02

    Hear the news

    “What did the city council post about the tram strike today?”

    search_web bills 2 credits for each provider page, then scrape_page 1 credit a page.

  • 03

    See the page

    “Send me a screenshot of the venue's page for Saturday's concert.”

    capture_screenshot returns an image URL for 5 credits.

  • 04

    Watch the ferry

    prompt

    openclaw automations create "0 8 * * *" "With Wayfern, read the ferry operator's service page. Tell me only if a sailing is cancelled." --name ferry --session isolated

    Send the result to Telegram with openclaw automations edit <id> --announce --channel telegram.

Tools

What OpenClaw 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

Exec approvals
OpenClaw's exec approvals can ask in chat with /approve <id>. The skill route runs curl through exec.
Credits
Each automation run spends credits for its tool calls. get_usage shows the balance and is free.

More agents

All AI agents

Connect OpenClaw 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