URLpipe is an MCP server with 17 tools an agent can call, among them capture_console_errors, capture_pdf, capture_screenshot. It answers at https://urlpipe.dev/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 25 September 2026; the last check, on 8 November 2026, succeeded.
Read any page with its JavaScript run: Markdown, screenshots, metadata, console errors, Lighthouse.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
capture_console_errors | Exposes POST /console. Loads the page in headless Chrome and returns what it reported through console.error and console.warn during load, plus uncaught exceptions and unhandled promise rejections (not console.log). 1 credit. What you would Inputs: project_id, url, sync, max_age, residential, report_to |
capture_pdf | Exposes POST /pdf. Prints the whole rendered page to a PDF — JavaScript executed, web fonts and lazy-loaded images included, its headings as bookmarks. 1 credit, whichever options you use. Use it to archive or hand on a page as a document: Inputs: project_id, url, sync, max_age, residential, report_to |
capture_screenshot | Exposes POST /screenshot. Captures the whole rendered page as a PNG — JavaScript executed, web fonts and images included, exactly as a browser would draw it. 1 credit, whichever options you use. Use it to see a page rather than read it: lay Inputs: project_id, url, sync, max_age, residential, report_to |
detect_technologies | Exposes POST /technologies. Detects what a page is built with — CMS, e-commerce platform, JavaScript frameworks and libraries, analytics and tag managers, advertising and marketing tools, CDN, web server, programming language, payment provi Inputs: project_id, url, sync, max_age, residential, report_to |
extract_data | Exposes POST /extract. Reads the page and fills an object YOU define: pass `fields`, each with a name, a type and a description of what to take from the page, and get back exactly those keys in that order. Anything the page does not give co Inputs: project_id, url, sync, max_age, residential, report_to |
extract_keywords | Exposes POST /keywords. Returns the 5–15 terms and phrases that best represent the page, ordered by relevance — ranked by a language model, not by raw frequency. 15 credits. As with summarize_page: if you are going to reason over the result Inputs: project_id, url, sync, max_age, residential, report_to |
extract_metadata | Exposes POST /meta. Reads everything a page declares about itself — Open Graph, Twitter cards, meta tags, JSON-LD, microdata and links — into one object with the same keys on every page: title, description, site name, kind of page, language Inputs: project_id, url, sync, max_age, residential, report_to |
fetch_html | Exposes POST /html. Returns the page's HTML after JavaScript has run and redirects have been followed — the DOM a real browser sees, not the empty shell curl returns. 1 credit. Use it when you need the markup itself: a specific attribute, a Inputs: project_id, url, sync, max_age, residential, report_to |
fetch_markdown | Exposes POST /markdown. Renders the page in headless Chrome and converts its main content to clean Markdown — headings, lists, links and code kept, navigation, sidebars and cookie banners dropped. Start here when you want to READ a page. It Inputs: project_id, url, sync, max_age, residential, report_to |
get_request | Everything about one past request except its result: what was asked for, how long each stage took, whether it came from the store, and how the webhook delivery went. This is the metadata; get_result returns the page itself. Reach for this o Inputs: project_id, token |
get_result | Exposes GET /result/:token. Returns the result of a past request, in the same form the call that made it would have returned — Markdown as Markdown, a structured operation as its object, a screenshot as an image, a PDF as an embedded applic Inputs: project_id, token |
get_usage | What the organization's plan allows, how much of it is left this period, and what each operation costs. Worth reading before a run of expensive calls: the operations differ by seventeen times in price, so the difference between fetch_markdo |
list_projects | The projects this token can reach, each with how many requests it has made in the last 30 days and where its results are delivered. Start here: every other tool takes a project_id from this list. A project is the unit a request is billed an |
list_requests | A project's recent requests, newest first, with each one's token. Look here before fetching a page: if somebody already pulled it, passing that token to get_result returns the same result for nothing. A /scrape appears as one entry — its pe Inputs: project_id, url, operation, labels, limit, offset |
run_lighthouse_audit | Exposes POST /lighthouse. Runs a real Google Lighthouse audit against the live page: performance, accessibility, best-practices and SEO scores plus Core Web Vitals. 2 credits — dearer than a page fetch because the audit runs in its own limi Inputs: project_id, url, sync, max_age, residential, report_to |
scrape_url | Exposes POST /scrape. Runs any subset of the other operations in one request, served from a single page visit where possible. Each operation is billed and stored exactly as the individual call would be, so this is not a discount — with one Inputs: project_id, url, sync, max_age, residential, report_to |
summarize_page | Exposes POST /summarize. Returns a concise Markdown summary of the page's main content, with the navigation, ads and boilerplate left out. The most expensive operation we sell, at 17 credits, because it runs a language model over the page. Inputs: project_id, url, sync, max_age, residential, report_to |
Every block below points at https://urlpipe.dev/mcp. Pick your client and copy.
claude mcp add --transport http urlpipe https://urlpipe.dev/mcp
{
"mcpServers": {
"urlpipe": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://urlpipe.dev/mcp"]
}
}
}{
"mcpServers": {
"urlpipe": {
"url": "https://urlpipe.dev/mcp"
}
}
}{
"servers": {
"urlpipe": {
"type": "http",
"url": "https://urlpipe.dev/mcp"
}
}
}{
"context_servers": {
"urlpipe": {
"url": "https://urlpipe.dev/mcp"
}
}
}{
"mcpServers": {
"urlpipe": {
"serverUrl": "https://urlpipe.dev/mcp"
}
}
}{
"mcpServers": {
"urlpipe": {
"url": "https://urlpipe.dev/mcp"
}
}
}name: URLpipe
version: 0.0.1
schema: v1
mcpServers:
- name: URLpipe
type: streamable-http
url: https://urlpipe.dev/mcp{
"mcpServers": {
"urlpipe": {
"httpUrl": "https://urlpipe.dev/mcp"
}
}
}{
"mcpServers": {
"urlpipe": {
"type": "http",
"url": "https://urlpipe.dev/mcp"
}
}
}{
"mcpServers": {
"urlpipe": {
"url": "https://urlpipe.dev/mcp"
}
}
}goose://extension?url=https%3A%2F%2Furlpipe.dev%2Fmcp&type=streamable_http&id=urlpipe&name=URLpipe
It answered our last check on 8 November 2026 in 166 ms. Over 4 checks since 25 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by urlpipe.dev and served from urlpipe.dev, the vendor's own domain: https://urlpipe.dev/mcp.
17, as returned by the server's own tools/list on 15 November 2026: capture_console_errors, capture_pdf, capture_screenshot, detect_technologies, extract_data, extract_keywords, extract_metadata, fetch_html, and 9 more.
It answered our last check on 8 November 2026 in 166 ms. Over 4 checks since 25 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://urlpipe.dev/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: dev.urlpipe. Endpoint host: urlpipe.dev. ARD identifier: urn:air:dev.urlpipe:mcp:mcp.
First indexed 25 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.