mcpbeat Sign in

Pagesnap MCP Server

by sslip-142-93-197-141-pagesnap Your server? Claim it
not responding

Pagesnap is listed as active in the registry but did not answer our last check. It exposes 12 tools.

Stateless MCP: 11 web tools, 4 prompts, 4 docs/usage resources, and structured outputs. Free.

The linked repository no longer exists on GitHub — it was deleted or made private.

Uptime history 67 days of history · worst day 0%
67 days agonow
0.0%
Uptime 24h
0 of 91 checks
12
Tools
read from the server
8000 ms
Response time
average over 24h
open, no key
Access
streamable-http

What changed 1

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 3 September 2026. No other catalogue keeps this.

3 Sep a tool appeared find_feeds

Pagesnap does not always answer

Over the last week it answered 0.0% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.

run in your terminal
claude mcp add pagesnap --transport http https://pagesnap.142-93-197-141.sslip.io/mcp
Settings → Connectors → Add custom connector, then paste this address
https://pagesnap.142-93-197-141.sslip.io/mcp
~/.codex/config.toml
[mcp_servers.pagesnap]
url = "https://pagesnap.142-93-197-141.sslip.io/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "pagesnap": {
      "url": "https://pagesnap.142-93-197-141.sslip.io/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "pagesnap": {
      "type": "http",
      "url": "https://pagesnap.142-93-197-141.sslip.io/mcp"
    }
  }
}

Available tools 12

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

crawl
crawl_site
Crawl up to 25 robots-aware, same-origin pages and concatenate clean Markdown with a source header for each page. Useful for RAG ingestion and documentation discovery. Example: crawl_site({ url: "https://example.com/docs", limit: 5, max_depth: 2 }).
extract
extract_structured
Deterministically extract JSON-LD, microdata, RDFa-lite, Open Graph, Twitter cards, and normalized schema entities from a URL. Uses a browser only when bot protection blocks the fetch path. Example: extract_structured({ url: "https://example.com/product", max_chars: 30000 }).
feeds
find_feeds
Find and verify RSS, Atom, or JSON Feed endpoints for a public website. Checks declared alternate links and common platform paths, then returns feed metadata and sample items. Example: find_feeds({ url: "https://example.com/blog" }).
generate
generate_llms_txt
Crawl a public documentation site with robots.txt and sitemap rules, then generate both the concise llms.txt navigation file and a concatenated llms-full.txt Markdown corpus. Example: generate_llms_txt({ url: "https://example.com/docs", limit: 10 }).
meta
get_meta
Return title, description, Open Graph image, favicon, site name, canonical URL, author and published time for a public URL without rendering the full page. Example: get_meta({ url: "https://example.com/article" }).
monitor
create_monitor
Create a persisted text, visual, or metadata monitor. A Pagesnap API key is required. The webhook signing secret is returned only by this call. Example: create_monitor({ url: "https://example.com", mode: "text", interval: "24h" }).
monitors
list_monitors
List the change monitors owned by the authenticated Pagesnap API key. Example: list_monitors({}).
pdf
pdf_url
Render a web page to a PDF file and return a temporary download link (valid 1 hour). Example: pdf_url({ url: "https://example.com", format: "A4", page_numbers: true }).
screenshot
screenshot_url
Render a web page in a headless browser and return a screenshot image (plus a temporary URL to the file, valid 1 hour). Use it to visually verify pages, capture charts, or show a human what a page looks like. Example: screenshot_url({ url: "https://example.com", width: 1280, height: 800, format: "png" }).
upgrade
upgrade_plan
Create a crypto payment invoice for this API key and return wallet-ready payment options. Calling this tool creates a new order; pay exactly one option. Example: upgrade_plan({ plan: "pro" }).
url
read_url
Fetch a public web page and return extracted main content as Markdown (or plain text / JSON with title, author, links, and images). It can handle JavaScript-rendered pages (set render=true to force a headless browser), PDFs, and plain text; extraction can omit content on unusual layouts. Example: read_url({ url: "https://example.com", format: "markdown" }). Keyless per-call HTTP alternative: https://pagesnap.142-93-197-141.sslip.io/x402/v1/read ($0.002 USDC on Base).
usage
usage
Show the current plan, trial status, remaining quota, and paid or link-based ways to keep Pro. Example: usage({}).

Endpoints

URLTransportStateLatencyChecked
https://pagesnap.142-93-197-141.sslip.io/mcp streamable-http answering 8000 ms 13 min ago

Alternatives to Pagesnap

same job, measured the same way
webforJ MCP Server
by webforj

WebforJ's MCP server, provides tools, resources, prompts for scaffolding and developing webforJ apps

9 tools answering
Prompt Guard MCP
by robertoyanguas-ops

Scans untrusted web pages, emails, or tool outputs for prompt injections and returns sanitized tex

2 tools answering
Gopher & Gemini MCP Server
by cameronrye

Browse Gopher and Gemini resources safely: SSRF protection, TLS/TOFU, structured JSON output.

179 installs/wk local only
liz's doc public knowledge
by liz6

Read-only search and Markdown access to liz's public docs, prompts, resources, and an MCP App.

5 tools answering
Plato's Kallipolis
by handongzhen101-jpg

Read-only MCP tools for AI agent discovery, structured resources, and NIULAI information.

6 tools answering
S
Simple MCP HTTP
by oleksii-donets

A Test MCP server that provides tools, promts and resources

local only
Simple MCP
by oleksii-donets

A Test MCP server that provides tools, promts and resources

local only
Streamparse
by mukundakatta

Parse partial / truncated / messy JSON for LLM tool calls and structured outputs.

57 installs/wk local only

Pagesnap — questions

Answers built from our own checks of this server.

What can Pagesnap do?
It exposes 12 tools, read directly from the server on our last check. Among them: crawl_site, create_monitor, extract_structured, find_feeds, generate_llms_txt, get_meta and 6 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Pagesnap working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 0 of 91 checks got a reply (0.0%), average response time 8000 ms. The bar chart above shows every period we have measured.
Is Pagesnap still maintained?
The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.
The registry lists Pagesnap as active — why does it not respond?
The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.
How do I connect Pagesnap?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Pagesnap need an API key?
No. Pagesnap completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 12 of them are readable on this page. This is what we observed, not what the docs claim.