PageWire is answering right now. Last checked 15 min ago. It exposes 3 tools.
Web pages to Markdown, metadata and small crawls for agents. Free daily calls, then USDC x402/MPP.
Today is the operative word: we check PageWire every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 15 min ago.
claude mcp add web --transport http https://pagewire.dev/mcp
{
"mcpServers": {
"web": {
"url": "https://pagewire.dev/mcp"
}
}
}
[mcp_servers.web]
url = "https://pagewire.dev/mcp"
{
"mcpServers": {
"web": {
"url": "https://pagewire.dev/mcp"
}
}
}
{
"mcpServers": {
"web": {
"url": "https://pagewire.dev/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
page_metadata
page_to_markdown
crawl_site
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://pagewire.dev/mcp | streamable-http | answering | 160 ms | 15 min ago |
Web pages and whole sites to clean Markdown for RAG and AI agents. Crawls links and sitemaps.
Three MCP tools: fetch_page, fetch_pages_batch, search_web. Ad-free Markdown for AI agents.
Web scraping and Iranian-web data tools for AI agents: JS rendering, proxies, Markdown output.
Web toolkit for AI agents: read any URL as Markdown, screenshot, extract data, or crawl a site.
Web toolkit for AI agents: read any URL as Markdown, screenshot, extract data, or crawl a site.
Pay-per-call web scraping for AI agents via x402 on Base USDC. Six tools, no signup.
Web scraping for agents: scrape, crawl, map, search and extract pages as clean markdown or JSON.
Scrape to markdown, map and crawl sites, drive a real browser. Pay per call, no API key, no signup.
Answers built from our own checks of this server.