WebLens
Scrape, crawl, map and extract the web. Pay per call in USDC, no account or API key.
我該用這個嗎
品質與安全性
發現項目（9）
- HIGHTool poisoning patterns detected
- LOWTool 'screenshot' description lacks action verb在 screenshot 中
- LOWTool 'extract_data' description lacks action verb在 extract_data 中
- LOWTool 'smart_extract' description lacks action verb在 smart_extract 中
- LOWTool 'extract_pdf' description lacks action verb在 extract_pdf 中
- LOWTool 'intel_company' description lacks action verb在 intel_company 中
- LOWTool 'intel_competitive' description lacks action verb在 intel_competitive 中
- LOWTool 'memory_set' description lacks action verb在 memory_set 中
- INFOTool description contains placeholder or incomplete text在 search_discussions 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"weblens": {
"url": "https://api.weblens.dev/mcp"
}
}
}遠端端點
https://api.weblens.dev/mcpstreamable-http它能做什麼
工具清單
工具（36）
⚪preview_endpoint(endpoint, url)
FREE. See what a paid WebLens endpoint costs and what it returns before paying: the live price, a one-line summary, and a recorded sample of the exact response shape. Endpoints with no paid upstream (/fetch/basic, /contents, /map) also run a real truncated LIVE preview when you pass a url; SerpAPI- and Anthropic-backed endpoints return the recorded sample only, because free live runs there would burn upstream credits. Price: free
輸入結構描述
{
"type": "object",
"properties": {
"endpoint": {
"type": "string",
"description": "Paid endpoint path to preview, e.g. \"/answer\""
},
"url": {
"type": "string",
"description": "Fetch-backed endpoints only (/fetch/basic, /contents, /map): run a real truncated preview of this URL"
}
},
"required": [
"endpoint"
]
}🟢fetch_webpage(url, timeout, cache, cacheTtl)
Fetch and convert a webpage to clean markdown. Fast, no JavaScript rendering. Price: $0.002
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The URL to fetch"
},
"timeout": {
"type": "number",
"minimum": 5000,
"maximum": 30000,
"description": "Request timeout in ms (default 10000)"
},
"cache": {
"type": "boolean",
"description": "Serve from cache when available (default true; cached responses cost 70% less)"
},
"cacheTtl": {
"type": "number",
"minimum": 60,
"maximum": 86400,
"description": "Cache TTL in seconds (default 3600)"
}
},
"required": [
"url"
]
}🟢fetch_webpage_pro(url, waitFor, timeout)
Fetch webpage with full JavaScript rendering. Use for SPAs and dynamic content. Price: $0.006
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The URL to fetch"
},
"waitFor": {
"type": "string",
"description": "CSS selector to wait for before capturing content (e.g. \".content\")"
},
"timeout": {
"type": "number",
"minimum": 5000,
"maximum": 30000,
"description": "Request timeout in ms (default 15000)"
}
},
"required": [
"url"
]
}⚪screenshot(url, width, height, fullPage)
Capture a screenshot of a webpage. Returns base64 PNG image. Price: $0.008
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The URL to screenshot"
},
"width": {
"type": "number",
"minimum": 320,
"maximum": 3840,
"description": "Viewport width (default 1280)"
},
"height": {
"type": "number",
"minimum": 240,
"maximum": 2160,
"description": "Viewport height (default 720)"
},
"fullPage": {
"type": "boolean",
"description": "Capture full page scroll"
}
},
"required": [
"url"
]
}🟡search_web(query, limit, includeContent, contentResults, contentChars)
Search the web and get real-time results with snippets. Set includeContent to also fetch the top result pages as markdown (+$0.0015/result). Price: $0.015
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search query"
},
"limit": {
"type": "number",
"description": "Number of results (default: 10)"
},
"includeContent": {
"type": "boolean",
"description": "Also fetch top result pages as markdown (+$0.0015/result)"
},
"contentResults": {
"type": "number",
"description": "How many top results to fetch content for (1-10, default: 5)"
},
"contentChars": {
"type": "number",
"minimum": 500,
"maximum": 20000,
"description": "Per-page content character cap (default 8000)"
}
},
"required": [
"query"
]
}🟢search_news(query, limit)
Search Google News for real-time articles with source, date, and thumbnail. Price: $0.015
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "News search query"
},
"limit": {
"type": "number",
"description": "Number of results (default: 10, max: 20)"
}
},
"required": [
"query"
]
}🟢search_images(query, limit)
Search Google Images for direct image URLs with dimensions, thumbnails, and source pages. Price: $0.015
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Image search query"
},
"limit": {
"type": "number",
"description": "Number of results (default: 10, max: 20)"
}
},
"required": [
"query"
]
}🟢search_places(query, location, limit)
Search local businesses via Google Local: names, addresses, ratings, reviews, phone, website, coordinates. Price: $0.045
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "What to search for (e.g. coffee shops)"
},
"location": {
"type": "string",
"description": "Free-text location bias, e.g. \"Austin, Texas\""
},
"limit": {
"type": "number",
"description": "Number of results (default: 10, max: 20)"
}
},
"required": [
"query"
]
}🟢search_shopping(query, limit)
Search Google Shopping for products with prices, sellers, ratings, and links. Price: $0.015
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Product search query"
},
"limit": {
"type": "number",
"description": "Number of results (default: 10, max: 20)"
}
},
"required": [
"query"
]
}🟢search_scholar(query, limit)
Search Google Scholar for academic papers with snippets, publication info, and citation counts. Price: $0.015
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Academic search query"
},
"limit": {
"type": "number",
"description": "Number of results (default: 10, max: 20)"
}
},
"required": [
"query"
]
}🟢search_autocomplete(query, limit)
Get Google Autocomplete suggestions for a partial query — keyword research and intent discovery. Price: $0.015
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Partial query to complete"
},
"limit": {
"type": "number",
"description": "Max suggestions (default: 10, max: 20)"
}
},
"required": [
"query"
]
}🟢search_trends(query)
Get Google Trends interest-over-time timeline for a query. Price: $0.015
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Topic to get trend data for"
}
},
"required": [
"query"
]
}🟢youtube_transcript(videoId, lang)
Get the full transcript of a YouTube video with timestamps. Accepts a video ID or any YouTube URL. Price: $0.03
輸入結構描述
{
"type": "object",
"properties": {
"videoId": {
"type": "string",
"description": "YouTube video ID (e.g. dQw4w9WgXcQ) or full video URL"
},
"lang": {
"type": "string",
"description": "Transcript language code (default: video default)"
}
},
"required": [
"videoId"
]
}🟢get_contents(urls, maxChars, timeout)
Fetch 1-20 URLs and get clean markdown per page, truncated to a character cap. Price: $0.0015/URL
輸入結構描述
{
"type": "object",
"properties": {
"urls": {
"type": "array",
"items": {
"type": "string"
},
"description": "URLs to fetch (1-20)"
},
"maxChars": {
"type": "number",
"minimum": 500,
"maximum": 50000,
"description": "Per-page content character cap (default 20000)"
},
"timeout": {
"type": "number",
"minimum": 5000,
"maximum": 30000,
"description": "Per-URL timeout in ms (default 10000)"
}
},
"required": [
"urls"
]
}🟢answer_question(query, sources)
Get a grounded answer with inline [n] citations: searches the web, fetches sources, and answers strictly from them. Price: $0.05
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The question to answer"
},
"sources": {
"type": "number",
"description": "Web sources to search, fetch, and cite (1-5, default: 3)"
}
},
"required": [
"query"
]
}🟢extract_data(url, schema, instructions)
Extract structured data from a webpage using a JSON schema. AI-powered extraction. Price: $0.03
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The URL to extract from"
},
"schema": {
"type": "object",
"description": "JSON schema defining the data structure to extract"
},
"instructions": {
"type": "string",
"description": "Natural language instructions to guide extraction"
}
},
"required": [
"url",
"schema"
]
}🟢smart_extract(url, query)
Extract data using natural language. AI understands what you want. Price: $0.035
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The URL to extract from"
},
"query": {
"type": "string",
"description": "What data to extract (natural language)"
}
},
"required": [
"url",
"query"
]
}⚪research(query, resultCount)
One-stop research: searches web, fetches top results, and summarizes findings. Price: $0.08
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Research topic or question"
},
"resultCount": {
"type": "number",
"description": "Number of sources to analyze (default: 5)"
}
},
"required": [
"query"
]
}🟢deep_research(query, depth)
Multi-step cited research in one call: plans sub-questions, searches each, fetches and dedupes sources, then synthesizes an answer with inline [n] citations, key findings, and gaps. Unlike `research` ($0.08, one search + summary) this decomposes the question and cites every claim. SLOW: a standard run takes ~30-60 seconds — use a generous client timeout and do not retry on timeout. Price: $0.20 standard (3 sub-questions, 8 sources) / $0.35 deep (5 sub-questions, 12 sources)
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The research question (1-500 chars)"
},
"depth": {
"type": "string",
"enum": [
"standard",
"deep"
],
"description": "Research tier: standard = 3 sub-questions / 8 sources ($0.20); deep = 5 / 12 ($0.35). Default: standard"
}
},
"required": [
"query"
]
}🟢extract_pdf(url)
Extract text and metadata from a PDF document. Price: $0.004
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "URL of the PDF to extract"
}
},
"required": [
"url"
]
}🟢compare_urls(urls, focus)
Compare 2-3 webpages and get AI-generated analysis of differences. Price: $0.05
輸入結構描述
{
"type": "object",
"properties": {
"urls": {
"type": "array",
"items": {
"type": "string"
},
"description": "URLs to compare (2-3)"
},
"focus": {
"type": "string",
"description": "What to focus comparison on"
}
},
"required": [
"urls"
]
}🟢batch_fetch(urls)
Fetch multiple URLs in parallel. Efficient for bulk operations. Price: $0.0015/URL
輸入結構描述
{
"type": "object",
"properties": {
"urls": {
"type": "array",
"items": {
"type": "string"
},
"description": "URLs to fetch (2-20)"
}
},
"required": [
"urls"
]
}⚪domain_intel(domain)
Everything about a domain in one call: who registered it and when, when it expires, its DNS records, the mail and DNS providers behind them, the SaaS vendors its TXT verification tokens reveal (Google Workspace, Microsoft 365, Salesforce, Atlassian, Okta, …), SPF/DMARC posture, and risk flags like newly-registered or no-registrar-lock. Use for vendor due diligence, security triage, phishing checks and prospect research. Price: $0.005
輸入結構描述
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"description": "Domain to inspect, e.g. \"stripe.com\". A full URL is reduced to its hostname."
}
},
"required": [
"domain"
]
}🟢project_due_diligence(domain, tokenAddress, chain)
Off-chain due diligence on a project's web presence — the half an on-chain rug checker cannot see. Returns domain age and registrar, whether a team page, whitepaper, docs and socials exist, whether the site is an off-the-shelf template, and a cross-check of a contract address against the addresses actually printed on the project's own website (a mismatch is a strong impersonation signal). Gives weighted risk signals and an A-F grade. Reads NOTHING on-chain — pair it with a contract/liquidity checker. Price: $0.05
輸入結構描述
{
"type": "object",
"properties": {
"domain": {
"type": "string",
"minLength": 3,
"maxLength": 253,
"description": "Project website, e.g. \"example.org\""
},
"tokenAddress": {
"type": "string",
"minLength": 20,
"maxLength": 80,
"description": "Optional contract address to cross-check against the site"
},
"chain": {
"type": "string",
"minLength": 2,
"maxLength": 32,
"description": "Optional chain label, e.g. base, ethereum, solana"
}
},
"required": [
"domain"
]
}⚪package_intel(name, registry)
Should you depend on this package? One call returns version, license, deprecation status WITH the maintainer's reason, weekly/monthly downloads, last release date, maintainer count, npm's quality/popularity/maintenance scores, and health signals (deprecated, no-recent-release, no-license, single-maintainer, no-public-repository). Supports npm and PyPI. Price: $0.003
輸入結構描述
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Package name, e.g. \"express\" or \"@scope/pkg\""
},
"registry": {
"type": "string",
"enum": [
"npm",
"pypi"
],
"description": "Registry to look in (default npm)"
}
},
"required": [
"name"
]
}⚪detect_tech(url)
What a website is built and run on, from a single fetch: framework, CMS, ecommerce platform, CDN, analytics, payments, support widgets and web server — each reported with the response header or HTML marker that proves it. Use for competitive research, sales prospecting and vendor due diligence. Price: $0.005
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Site URL to fingerprint"
}
},
"required": [
"url"
]
}🟢search_discussions(query, limit, sort)
What Hacker News said about a topic: matching stories with points, comment counts and links to the threads, plus aggregates — total matches, points and comments returned, most-submitted domains, and when it was first and last discussed. Price: $0.004
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "What to search Hacker News for"
},
"limit": {
"type": "number",
"minimum": 1,
"maximum": 50,
"description": "Stories to return (default 10)"
},
"sort": {
"type": "string",
"enum": [
"relevance",
"recent"
],
"description": "Ranking (default relevance)"
}
},
"required": [
"query"
]
}⚪map_site(url, limit, include, exclude, timeout)
Discover a site's URLs without fetching page content — reads robots.txt sitemap directives, sitemap.xml and nested sitemap indexes, falling back to homepage link extraction. Price: $0.004
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Site URL to map"
},
"limit": {
"type": "number",
"description": "Maximum URLs to return (1-5000, default: 1000)"
},
"include": {
"type": "array",
"items": {
"type": "string"
},
"description": "Only URLs whose path+query contains one of these substrings"
},
"exclude": {
"type": "array",
"items": {
"type": "string"
},
"description": "Skip URLs whose path+query contains one of these substrings"
},
"timeout": {
"type": "number",
"minimum": 5000,
"maximum": 30000,
"description": "Timeout in ms (default 10000)"
}
},
"required": [
"url"
]
}🟢crawl_site(url, limit, maxDepth, include, exclude, ...)
Crawl a site and get clean markdown for every page in one synchronous call (no polling). Same-host BFS with depth and page-budget limits, robots.txt honoured by default. Price: $0.0015 per requested page (1-25) — you are billed for the requested budget, not the pages returned
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Start URL — the crawl stays on this host"
},
"limit": {
"type": "number",
"description": "Page budget (1-25, default: 10) — charged per requested page"
},
"maxDepth": {
"type": "number",
"description": "Link depth from the start URL (0-3, default: 2)"
},
"include": {
"type": "array",
"items": {
"type": "string"
},
"description": "Only crawl URLs whose path+query contains one of these substrings"
},
"exclude": {
"type": "array",
"items": {
"type": "string"
},
"description": "Skip URLs whose path+query contains one of these substrings"
},
"respectRobots": {
"type": "boolean",
"description": "Honour robots.txt (default: true; disable only for sites you control)"
},
"maxChars": {
"type": "number",
"minimum": 500,
"maximum": 50000,
"description": "Per-page content character cap (default 8000)"
},
"timeout": {
"type": "number",
"minimum": 5000,
"maximum": 30000,
"description": "Per-page timeout in ms (default 10000)"
}
},
"required": [
"url"
]
}🟢fetch_resilient(url, timeout)
Resilient fetch with automatic fallback: native scraper first, then headless Chromium for JS-rendered or bot-walled pages. Price: $0.008
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The URL to fetch"
},
"timeout": {
"type": "number",
"minimum": 5000,
"maximum": 30000,
"description": "Timeout in ms (default 10000)"
}
},
"required": [
"url"
]
}⚪intel_company(target)
Company intelligence deep dive: tech stack, funding, team, competitors, news. Price: $1.00
輸入結構描述
{
"type": "object",
"properties": {
"target": {
"type": "string",
"description": "Company name or domain to research"
}
},
"required": [
"target"
]
}⚪intel_market(topic, depth, focus)
AI-powered market research report with trends, key players, and data points. Price: $5.00
輸入結構描述
{
"type": "object",
"properties": {
"topic": {
"type": "string",
"description": "Market or industry topic to research"
},
"depth": {
"type": "string",
"enum": [
"quick",
"standard",
"comprehensive"
],
"description": "Research depth (default standard)"
},
"focus": {
"type": "string",
"description": "Optional focus area"
}
},
"required": [
"topic"
]
}⚪intel_competitive(company, maxCompetitors, focus)
Competitive analysis: feature matrix, pricing, SWOT analysis. Price: $8.00
輸入結構描述
{
"type": "object",
"properties": {
"company": {
"type": "string",
"description": "Company to analyze"
},
"maxCompetitors": {
"type": "number",
"description": "Max competitors to include (default: 5)"
},
"focus": {
"type": "string",
"description": "Optional focus area"
}
},
"required": [
"company"
]
}⚪intel_site_audit(url)
Comprehensive SEO, performance, and security audit with scoring. Price: $0.75
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "URL to audit"
}
},
"required": [
"url"
]
}🟡monitor_create(url, webhookUrl)
Create a URL change detection monitor with webhook notifications. Price: $0.01
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "URL to monitor for changes"
},
"webhookUrl": {
"type": "string",
"description": "Webhook URL for change notifications"
}
},
"required": [
"url",
"webhookUrl"
]
}🟡memory_set(key, value, ttl)
Store key-value data in persistent agent memory. Price: $0.001
輸入結構描述
{
"type": "object",
"properties": {
"key": {
"type": "string",
"description": "Storage key (max 256 chars)"
},
"value": {
"description": "Value to store (any JSON)"
},
"ttl": {
"type": "number",
"description": "Time to live in hours (1-720, default: 168)"
}
},
"required": [
"key",
"value"
]
}社群
證據