MCP tool reference · #441 of 563 by publishers
web_extract
Exposed by 17 servers from 9 publishers, read from the live servers by the Serverdex check; most of them sit in Crypto & Web3; 94.1% of them take a url parameter; the most-starred is x402 Agent Tools (4 stars).
web_extract(url: string, max_length?: number, payment_signature?: string, x_api_key?: string, …)Parameters
share = % of the 17 servers whose schema has it · required = % of those that mark it required| Parameter | Type | Share | Required | Usual description |
|---|---|---|---|---|
| url | string | 94.1% | 100% | Full URL to extract (must start with http:// or https://) |
| max_length | number | 35.3% | 0% | Maximum markdown character length to return (500-25000, default: 8000) |
| payment_signature | string | 35.3% | 0% | Optional x402 v2/v1 Base64 or JSON EIP-3009 USDC payment signature to unlock the full unmasked dataset directly via MCP |
| x_api_key | string | 35.3% | 0% | Optional ak_live_... 30-day Prepaid API Pass key to unlock the full unmasked dataset |
| include_links | boolean | 23.5% | 0% | Also return same-host links (max 100). Default false. |
| maxChars | integer | 11.8% | 0% | max markdown characters (default 20000, max 100000) |
| arguments | object | 5.9% | 100% | Tool-specific structured input object. Supply the required named fields described by its JSON Schema; source bytes must respect encoded size limits. Never inclu |
| format | string | 5.9% | 0% | — |
| idempotency_key | string | 5.9% | 100% | Stable job key; retry exactly the same inputs and payment mode with this key to recover safely. |
| links | string | 5.9% | 0% | 1 to include every link on the page (default 1) |
| max_chars | string | 5.9% | 0% | cap on the Markdown length, 1000-200000 (default 60000) |
| mode | string | 5.9% | 0% | "main" keeps the article/main region and drops nav/header/footer |
Source: the input schema each server returns for web_extract, aggregated over the 17 index-tier servers; type and description are the values most servers use. Rebuilt every 6 hours.
Servers with web_extract
13 of 17 · 9 publishers · 13 answering live · most-starred first, 3 per publisher| # | Server | Publisher | Category | ★ | Live | How it describes web_extract |
|---|---|---|---|---|---|---|
| 1 | x402 Agent Toolssignal-forge-ai · Crypto & Web3 | signal-forge-ai | Crypto & Web3 | 4 | yes | Structured JSON extraction from a web page: title, meta/OpenGraph, JSON-LD, headings, links, tables, contact emails, plus Markdown body. Price $0.04 USDC on Base via x402. |
| 2 | Crypto Perp Funding Arbitrage Radar MCPralf9090 · Crypto & Web3 | ralf9090 | Crypto & Web3 | 1 | yes | Extract clean, LLM-ready Markdown from any web URL while automatically scanning the page for hidden Prompt Injection traps targeting AI agents. |
| 3 | arXiv & OpenAlex Academic Search MCPralf9090 · Education & Reference | ralf9090 | Education & Reference | — | yes | Extract clean, LLM-ready Markdown from any web URL while automatically scanning the page for hidden Prompt Injection traps targeting AI agents. |
| 4 | Token Honeypot & EVM Pre-Flight Audit MCPralf9090 · Crypto & Web3 | ralf9090 | Crypto & Web3 | — | yes | Extract clean, LLM-ready Markdown from any web URL while automatically scanning the page for hidden Prompt Injection traps targeting AI agents. |
| 5 | Skavio USDC Payment Verification & Proof MCPskavio-eu · Finance | skavio-eu | Finance | — | yes | Extract human-visible text from one public HTTPS page under robots and size limits. Use for readable page text, not raw document fetching (web_fetch) or SHA256 change detection (web_monitor). This is a separately authenticated company Agent Tools relay; requires a valid Bearer API key, an enabled backend operation and an accepted payment mode. x402 returns a workload-specific quote and prepaid con |
| 6 | Nightshift Labs: link, token & signature pre-checksnightshift-labs-ai · Search & Web | nightshift-labs-ai | Search & Web | — | yes | Fetch any public web page and return clean Markdown of the main content plus title, meta description, word count and absolute links. Strips scripts, navigation and boilerplate. Good for feeding pages to an LLM. Price: $0.003 USDC on Base per call (x402). |
| 7 | Robotbase MCPwygogogo19 · Crypto & Web3 | wygogogo19 | Crypto & Web3 | — | yes | Extract structured data from one public page: tables (headers + rows), JSON-LD blocks, and Open Graph/Twitter/canonical/language metadata. When to use: the page has tables or schema.org JSON-LD you need as data, without an LLM. Do not use: when you only need the page text (web_fetch) or a screenshot (web_screenshot). Returns: {ok, url, final_url, title, meta:{description,image,site_name,type,canon |
| 8 | Robotbase Contentwygogogo19 · Search & Web | wygogogo19 | Search & Web | — | yes | Extract structured data from one public page: tables (headers + rows), JSON-LD blocks, and Open Graph/Twitter/canonical/language metadata. When to use: the page has tables or schema.org JSON-LD you need as data, without an LLM. Do not use: when you only need the page text (web_fetch) or a screenshot (web_screenshot). Returns: {ok, url, final_url, title, meta:{description,image,site_name,type,canon |
| 9 | Robotbase web3wygogogo19 · Crypto & Web3 | wygogogo19 | Crypto & Web3 | — | yes | Extract structured data from one public page: tables (headers + rows), JSON-LD blocks, and Open Graph/Twitter/canonical/language metadata. When to use: the page has tables or schema.org JSON-LD you need as data, without an LLM. Do not use: when you only need the page text (web_fetch) or a screenshot (web_screenshot). Returns: {ok, url, final_url, title, meta:{description,image,site_name,type,canon |
| 10 | YRUZ x402 toolsxzntexe · Crypto & Web3 | xzntexe | Crypto & Web3 | — | yes | Fetch any public web page and return its main content as clean Markdown (navigation, scripts and boilerplate removed) with title, description, language, canonical URL, author, publish date, headings, links and images. Built for agents that need to read or cite the web. Follows up to 5 redirects; HTML, plain text and JSON pages. Price: 0.005 USDC per call, paid with x402 (USDC on Base or Solana, no |
| 11 | Liquid Agentliquidagent · Crypto & Web3 | liquidagent | Crypto & Web3 | — | yes | PAID over x402 inside this tool call ($0.002 USDC on Base, Polygon or Arc): turn any public web page into clean Markdown. Built to feed the Website Watcher: search with web_search, extract the page, then scan it with link_check. Call once without payment to get the x402 PaymentRequired, then call again with the signed payment in _meta["x402/payment"]. |
| 12 | Oblique Marketsoblique-markets · AI & Agents | oblique-markets | AI & Agents | — | yes | Extract structured JSON from a web page: return URL, title, meta description, cleaned text, extraction timestamp, and payment status for agent workflows. $0.03/call via x402. |
| 13 | x402 Toolboxswiftbotlab · Crypto & Web3 | swiftbotlab | Crypto & Web3 | — | yes | Fetch a web page and return clean main text and Markdown plus title and metadata. Fetches a public URL (redirects followed and re-checked) and converts the HTML to clean text and Markdown: main/article content first, navigation/footers/scripts removed, links made absolute. Also returns title, description, language, canonical URL, headings and word count. Plain-text and JSON responses are returned |
Stars from GitHub as stored in the Serverdex index (re-read every 7 days per server); live = answered the last daily check of its hosted endpoint. The other 4 servers are reached from their publisher pages.