Hosted MCP server that lets an assistant read a live web page as clean text, screen it for prompt injection, and list a site's pages from its sitemaps.
What you can do
Read one public URL and get its title, metadata and boilerplate-stripped main text, with JS/SPA pages recovered without a browser and a prompt-injection screen flag
Enumerate a domain's sitemaps via robots.txt or a fallback sitemap file and return up to 20 page URLs with lastmod dates
Look up the paid x402 rail: metered depth layers, exact prices, pay-to address and how the 402 payment flow works
When to use it
Useful when an assistant needs to read a specific public page or map out a site's URLs without running a browser, and when you want a quick free preview before deciding whether the paid batch, monitoring or full sitemap endpoints are worth paying for.
Requirements
Remote streamable HTTP endpoint; no account, API key or environment variables are declared for the free tools. Paid depth layers require an x402-aware client that can pay in USDC on Base.
Before you install
The free tools are capped previews; batch extraction, change monitoring and full sitemap enumeration are paid per call in USDC on Base, so a client that can spend funds is needed. Fetched page content is untrusted and may carry prompt injection, which the server only flags. Requests go to a third-party hosted service.
Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.rezearcher%2Fweb-extract-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.
Free keyless live web read: fetch ONE public URL now and get the title, metadata and boilerplate-stripped main-content text (JS/SPA pages recovered without a browser), plus a prompt-injection screen flag. SSRF-guarded. Markdown, the full link graph and 10-URL batches are in the paid /web/extract ($0.003) — call get_premium_access.
Parametersurlrequiredfields
sitemap_preview
Free keyless site enumeration: discover a domain's sitemaps (robots.txt, fallback /sitemap.xml) and return up to 20 page URLs with lastmod. The paid /web/sitemap ($0.003) returns up to 5000 URLs across 10 sitemap files with a substring filter — call get_premium_access.
Parameterssiterequiredcontains
get_premium_access
Return the paid x402 rail: the metered depth layers (hosted 10-ATS search, normalized compensation, per-company hiring-intent signal, company enrichment, email deliverability) with exact prices (USDC on Base), the pay-to address, and how the 402 flow works. No account; an x402-aware client pays inline from the agent's wallet.
Takes no parameters.
Version history
2
v0.1.1LatestNov 1, 2026
v0.1.0Oct 31, 2026
Score
100%
100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.