MCP serverdev.urlpipe/mcp
Read any page with its JavaScript run: Markdown, screenshots, metadata, console errors, Lighthouse.
Overview
Score?
UNRATED 0.474
of what a free look can see, on 10 looks
Looks
11
last 10 hr ago
Tools
14
changed 3 days ago
More info
URL
urlpipe.dev/mcp
streamable-http
Says it is
urlpipe 1.3.0
protocol 2025-06-18
In the record since
8 days ago
Among servers18,413 with a card
0median 0.606 · this server 0.474 · highest on record 0.8561
Toolsfrom sha256:4908b1c37f…c5fce4 · +0 −0 3 days ago
| Tool | Schema |
|---|---|
| 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 pro |
input · output |
| 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 op |
input · output |
| 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 wi |
input · output |
| 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 |
input · output |
| 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.
Us |
input · output |
| 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 |
input · output |
| 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 m |
input · output |
| 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 o |
input · output |
| 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
sev |
input · output |
| 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 |
input · output |
| 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 sam |
input · output |
| 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 — dea |
input · output |
| 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 ind |
input · output |
| 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 |
input · output |
Verify it yourself
npx teppi-check https://urlpipe.dev/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M3E493R8RWKNDD5S6QX9PNDD