WebExtract
Server Details
Web page to structured JSON: product, tables, metadata. 20 free calls/day, x402.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- Repository
- nyx464664816-stack/webextract
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
Both tools fetch the same kind of page under identical constraints (HTML-only, robots.txt, no JS/PDF), so their core operation overlaps heavily; the only real differentiators are output format and price. The descriptions do make the boundary usable—structured JSON vs Markdown-only—but this is arguably one operation with a parameter difference rather than two distinct tools.
Both names use snake_case and are readable, but they follow different conventions: extract_url is verb_noun while page_markdown is noun_modifier. With only two tools there is no predictable pattern an agent can extrapolate.
Two tools is thin for a web-extraction server, especially when they largely duplicate the same fetch operation. It is not egregiously over- or under-scoped, but adding batch extraction or a structured-fields option would justify the surface better.
Single-page HTML extraction is covered for both Markdown and fixed-schema JSON, which are the core use cases. However, notable gaps remain: no batch/multi-URL extraction, no crawling or link discovery, no custom schema selection, and no raw HTML fallback—limitations that will cause workarounds for crawling-oriented agents.
Available Tools
2 toolsextract_urlExtract web pageARead-onlyInspect
Fetch a public web page (robots.txt respected) and return clean Markdown plus fixed-schema JSON: article metadata, product/price, tables. HTML only, no JS execution, no PDF. Free 20 calls/day per IP; pass 'Authorization: Bearer ' for prepaid credits.
Inputs: url (required). Returns: url, tables, product, markdown, +8 more
page_markdownWeb page to MarkdownARead-onlyInspect
Fetch a public web page (robots.txt respected) and return clean Markdown only. HTML only, no JS execution, no PDF. Cheaper than extract_url (0.4 credit). Free 20 calls/day per IP; pass 'Authorization: Bearer ' for prepaid credits.
Inputs: url (required). Returns: url, title, markdown, final_url, +4 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Paid web extraction: markdown, structured JSON, market-rules and page-change checks via x402.
AI web extraction: send URLs + a JSON Schema, get clean structured data. Pay-per-use via x402.
Web page to JSON fields (by JSON Schema) for agents. Pay per call in USDC on Base via x402.
Clean product data from any URL. Schema.org + AI extraction. 200 free calls/month.
Related MCP Servers
- AlicenseAqualityBmaintenanceGives AI agents web pages as clean Markdown, links, metadata or JSON that follows your schema. Each call is paid in USDC on Base via x402 ($0.002-$0.02), with built-in spending limits.121,162 npmMIT
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to extract structured JSON data from web pages using presets or custom JSON schemas, with confidence scores and source snippets, paid per call via USDC on Base.-
- FlicenseNot gradedqualityBmaintenanceEnables converting webpages into structured JSON using CSS-selector schemas, with anti-bot handling and support for protected pages.-
- AlicenseAqualityFmaintenanceStructured web extraction for AI agents. Pass any URL and a prompt, get clean JSON data back. Native MCP server with 100 free requests/month.3794 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.