AI agents · MCP
One MCP server for Claude, ChatGPT, Codex, Cursor and 16 more. Your agent searches three engines, reads pages as markdown, and captures screenshots, from a browser that sites do not block.
https://api.wayfern.com/mcp 


ChatGPT → Remote MCP → Wayfern extract_data
Claude Code → Remote MCP → Wayfern capture_screenshot
Cursor → Remote MCP → Wayfern scrape_page
Gemini → Remote MCP → Wayfern search_web
OpenClaw → Remote MCP → Wayfern crawl_site
MCP Server → Remote MCP → Wayfern get_usage
Ask anything
Pick a chat. Each one shows the real tool, its inputs and what it cost. The domains and answers are sample data.
Sample chats
Pull the brand colours from northwind.dev and give them to me as CSS variables.
A practical agent loop
The agent picks a tool and fills in its inputs: a URL, a query, a selector, a JSON Schema.
An anti-detect Chromium loads the page, waits for it, removes cookie banners and retries on a residential exit when a site blocks it.
Markdown, JSON or an image URL comes back with credits_charged, so the agent knows the cost of each step.
tools/call
{
"name": "capture_screenshot",
"arguments": {
"url": "https://acme.dev/pricing",
"full_page": true,
"block_cookie_banners": true
}
}Result
{
"screenshot": {
"url": "https://…/screenshots/8c1f….png",
"urlExpiresAt": "2026-10-29T13:00:00.000Z",
"contentType": "image/png"
},
"credits_charged": 5
}The agent gets a link, not image bytes. It opens the image when it needs to look, and the link expires on its own.
Three ways in
Each way calls the same services, on the same balance, at the same rates.
Agents that speak MCP
Add the URL and sign in on wayfern.com with OAuth. 11 tools appear. Clients that send headers can use a wf_ token.
server
https://api.wayfern.com/mcpAgents with a shell
One SKILL.md file teaches Claude Code, Codex and others to call the REST API with curl and your token.
bash
mkdir -p ~/.claude/skills/wayfern
curl -fsSL https://wayfern.com/skills/wayfern/SKILL.md -o ~/.claude/skills/wayfern/SKILL.mdYour own code
Call the Web Data API for deterministic steps, or drive a Wayfern browser with Playwright over CDP.
bash
curl https://api.wayfern.com/api/v1/scrape \
-H "Authorization: Bearer $WAYFERN_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"url": "https://example.com"}'Workflows
After a deploy, the agent captures the page and checks that the change is visible.
Read the guide →Search Google, Bing and DuckDuckGo in one call, then read the pages that matter.
Read the guide →Turn a docs page, or a whole docs site, into clean markdown for the model.
Read the guide →Extract plans and prices as JSON that matches your schema, on a schedule.
Read the guide →Colours, logos, fonts and design tokens of a site, as structured data.
Read the use case →Crawl a site with path rules and feed each page to your RAG pipeline.
Read the use case →Reliable browser execution
The same options work from the MCP tools and the REST API. The guides show each one.
Wait for a CSS selector or a fixed delay. Tall pages scroll so lazy images load.
Cookie banners are dismissed, ads blocked, and any selector you name is hidden.
Set the viewport, emulate a phone, take the full page, one element, or slices.
Markdown, HTML, links, JSON that matches a schema, or an image URL that expires.
Chat apps and the agents inside them. They reach Wayfern from the cloud over the remote MCP server and sign in with OAuth.
Agents that run on your computer. MCP, the agent skill, the REST API and a Wayfern browser over CDP all work.
Agents that work on a schedule or wait for a message, and call Wayfern for the steps that need the live web.
For a client that is not on this list, and for scripts.
A remote Model Context Protocol server at https://api.wayfern.com/mcp. It gives an AI agent 11 tools to search the web, scrape pages, extract data, map and crawl sites, and capture screenshots, all in Wayfern's anti-detect browser.
Any client that supports remote MCP over Streamable HTTP. This page has setup steps for 20 agents, including Claude, ChatGPT, Claude Code, Codex, Cursor, VS Code and Gemini.
No. Clients that support MCP authorization open wayfern.com, and you sign in and click Allow. Clients that cannot do OAuth can send a wf_ token with the mcp scope in an Authorization header.
Use MCP when the model decides which page to read or which search to run. Use the REST API when your own code runs a fixed step, such as a nightly crawl. Both call the same services at the same rates.
Yes. Each tool that fetches from the live web uses credits from your account at the REST API rates, and each result reports credits_charged. list_search_engines, crawl_status and get_usage are free.
Open Tokens in the dashboard. Connected apps lists each OAuth connection with its last use. Revoke stops the next tool call.
Text loses layout, colour and what is visible above the fold. A screenshot lets a vision model check that a price, a banner or a plan column is really on the page.
Each call runs in an anti-detect Chromium with a generated fingerprint. In proxy mode auto, a request that a site blocks is retried on a residential exit. Wayfern cannot promise that every site loads.
No. capture_screenshot returns a download URL, so the model context gets a short link and the client fetches the image only when it needs it.
Paste the server URL into your client and sign in. The tools appear at once.
https://api.wayfern.com/mcp