URLpipe

호스팅된 MCP 서버로, 실제 Chrome에서 페이지를 렌더링합니다: Markdown, 스크린샷, 메타데이터, 콘솔 오류 및 Lighthouse

호스팅형 MCP 서버

npx add-mcp 'https://urlpipe.dev/mcp'

Claude Code, Codex, Cursor 등에 설치됩니다

문서

An MCP server that gives your AI agent a real browser

Most fetch tools do a plain HTTP GET, so a JavaScript site comes back empty. This one loads the page in a real browser first — hosted, one token, nothing to run locally.

By Roger Campos · Last updated: October 2026

TL;DR

URLpipe's MCP server is a remote, streamable-HTTP server at https://urlpipe.dev/mcp. Add it to your client with a bearer token and your agent gets 17 tools: rendered Markdown, HTML, screenshots it can look at, metadata, Lighthouse, console errors and more — every page loaded in real Chrome, at the same credits as the HTTP API.

See the API

Free plan, no credit card. 1,000 credits a month.

The problem

Why an agent needs a rendering fetch

The reference fetch MCP server — the one most tutorials install first — fetches a page with a plain HTTP GET and converts the HTML it gets back. That is fine for a blog. On a React, Vue or Angular app, the HTML is an empty container and a script tag, and the agent is handed nothing while believing it read the page.

Reference fetch server

URLpipe MCP server

How the page is loaded

HTTP GET (httpx), no JavaScript

Real headless Chrome, scripts run

Where it runs

On your machine (uvx / pip / Docker)

Hosted — nothing to install

Output

Markdown (Readability + markdownify), or raw

Markdown, rendered HTML, screenshot, metadata, Lighthouse, console, summary, keywords

Screenshots

Returned as an image the model can see

Cookie banners and ads

Removed with page_options

Cost

Free, open source

Credits from your URLpipe plan

The fetch server is the right tool when the pages are static and you want everything local and free. Reach for this one when the agent meets pages that need a browser, or when it needs to see a page, not only read it. Its source is at modelcontextprotocol/servers.

Setup

Connect your client

Create an organization token under MCP access in your dashboard, then give your client the URL and the header.

Three values are the whole setup: transport streamable HTTP, URL https://urlpipe.dev/mcp, and an Authorization: Bearer YOUR_TOKEN header. There is no OAuth flow and no local process. The token is not your project API key — see tokens and scopes below.

Claude Code

claude mcp add --transport http urlpipe https://urlpipe.dev/mcp \
  --header "Authorization: Bearer YOUR_TOKEN"

Cursor

~/.cursor/mcp.json (or.cursor/mcp.json in a project)

{
  "mcpServers": {
    "urlpipe": {
      "url": "https://urlpipe.dev/mcp",
      "headers": {
        "Authorization": "Bearer ${env:URLPIPE_MCP_TOKEN}"
      }
    }
  }
}

VS Code

{
  "inputs": [
    {
      "type": "promptString",
      "id": "urlpipe-token",
      "description": "URLpipe MCP token",
      "password": true
    }
  ],
  "servers": {
    "urlpipe": {
      "type": "http",
      "url": "https://urlpipe.dev/mcp",
      "headers": {
        "Authorization": "Bearer ${input:urlpipe-token}"
      }
    }
  }
}

Windsurf

{
  "mcpServers": {
    "urlpipe": {
      "serverUrl": "https://urlpipe.dev/mcp",
      "headers": {
        "Authorization": "Bearer ${env:URLPIPE_MCP_TOKEN}"
      }
    }
  }
}

Claude Desktop

Claude Desktop's config file starts local servers, so a remote server with a bearer header goes through the mcp-remote bridge, which needs Node.js. The header's space lives in the environment variable because some clients don't escape spaces in arguments:

{
  "mcpServers": {
    "urlpipe": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://urlpipe.dev/mcp",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer YOUR_TOKEN"
      }
    }
  }
}

Any other client that speaks streamable HTTP takes the generic shape in the MCP docs. Keep the token out of files you commit — the examples above read it from an environment variable or a prompt where the client supports it.

Or install it from a directory

The server is listed in the MCP directories, which set it up for you in the clients they support, and in the official MCP Registry as dev.urlpipe/mcp. Its registry entry and the setup for every client above are open source on GitHub.

Smithery Glama cursor.directory GitHub: URLpipe/mcp

Tools

The 17 tools

Twelve are the API endpoints, with the same arguments and the same responses. Five exist only here.

Tool

What it returns

Credits

fetch_markdown

The page's main content as Markdown

1

fetch_html

The rendered HTML, after JavaScript

1

capture_screenshot

A full-page screenshot, as an image the model can see

1

capture_pdf

The whole page as a PDF, as a file the client can save

1

capture_console_errors

Errors, warnings and uncaught exceptions the page logs

1

run_lighthouse_audit

Lighthouse scores and Core Web Vitals lab metrics

2

extract_metadata

Title, description, author, dates, image, favicon, feed

1

detect_technologies

What the site is built with: CMS, frameworks, analytics, CDN, with versions

1

extract_keywords

Keywords from the page, by an AI model

15

summarize_page

A summary of the page, by an AI model

17

extract_data

Data read off the page into the fields you define, by an AI model

24

scrape_url

Several of the above from one page visit

sum of its operations

list_projects

Your projects and their ids — every fetch names one

0

get_usage

Credits used and left, reset date, the price list

0

get_result

The result of an earlier call, by token

0

list_requests

What a project already fetched, filterable by label

0

get_request

One request in detail: timings, options, webhook delivery

0

Tell your agent once: fetch_markdown costs 1 credit and summarize_page costs 17 credits. If the agent will read the page itself, Markdown is both cheaper and the better input; the AI tools are for when the summary or the keyword list is the thing you're producing. The server says the same to the model when it connects.

Behavior

Async by default, even for an agent

A tool call returns a token straight away and the work continues in the background, exactly as the HTTP API does. Pass sync: true when the agent should wait and be handed the result; otherwise it collects the result with get_result. An async call also delivers to the project's webhook if one is configured, so an agent can start work your backend receives.

Every endpoint tool takes project_id and url, plus the options its endpoint takes — page_options, screenshot_options, max_age, residential, labels and idempotency_key for safe retries. Stored results are reused for free, so an agent that re-reads a page it read yesterday spends nothing.

Access

Tokens, scopes and limits

  • Organization tokens. One token reaches every project in the organization, which is why each fetch names a project_id. You can narrow a token to one project.
  • Read-only scope. A token can be limited to reading past results, usage and projects. It cannot fetch a page, so it cannot spend credits.
  • Expiry. Give a token an end date, or delete it to revoke it at once. It is shown once and stored as a hash.
  • Limits. 300 calls per 5 minutes per token — comfortably above one a second, sustained — and your plan's parallel-request limit.
  • The same bill. An MCP call spends exactly what the matching endpoint spends, from the same allowance. Failed fetches and reused results are free.

Limits

What it does not do

  • No interactive browsing. The agent can't click, type or fill forms. Each tool loads one URL and reports what it found — signed in, when the call names an auth profile.
  • No crawling. It doesn't discover or follow links on its own; the agent decides which URLs to fetch.
  • No OAuth sign-in. Authentication is a bearer header; clients that only support an OAuth connector need the bridge shown for Claude Desktop.
  • Public addresses only. Private, loopback and intranet addresses are refused.

Pricing

What it costs

Call

Credits

Free (calls/mo)

Starter (calls/mo)

Pro (calls/mo)

Scale (calls/mo)

/markdown

1 credit

1,000

20,000

55,000

175,000

/screenshot

1 credit

1,000

20,000

55,000

175,000

/meta

1 credit

1,000

20,000

55,000

175,000

Cache hits and failed requests cost nothing. Paid plans are never cut off: past the allowance, extra credits are $1.50 per 1,000 credits. See every plan.

Endpoints

The endpoints on this page

FAQ

Frequently asked questions

Connect your agent in two minutes.

Free plan, no card. Confirm your email and your API key is live — you'll be making real requests in minutes.