WebLens
Scrape, crawl, map and extract the web.
Community: Submitted by a user or imported; check the owner before granting accessOnlineNo sign-inGlobalFreeRead-only
What it can do
What data it sees
Do you need an account
No: the server works without sign-in
Scrape, crawl, map and extract the web. Pay per call in USDC, no account or API key.
How to connect
How to connect WebLens to Claude
The server address to paste into Claude settings:
https://api.weblens.dev/mcp
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect WebLens to ChatGPT
The server address to paste into ChatGPT settings:
https://api.weblens.dev/mcp
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect WebLens to Cursor
The server address to paste into Cursor settings:
https://api.weblens.dev/mcp
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (36)
Raw names from tools/list. Only developers need these.
| preview_endpoint | 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 |
| fetch_webpage | Fetch and convert a webpage to clean markdown. Fast, no JavaScript rendering. Price: $0.002 |
| fetch_webpage_pro | Fetch webpage with full JavaScript rendering. Use for SPAs and dynamic content. Price: $0.006 |
| screenshot | Capture a screenshot of a webpage. Returns base64 PNG image. Price: $0.008 |
| search_web | 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 |
| search_news | Search Google News for real-time articles with source, date, and thumbnail. Price: $0.015 |
| search_images | Search Google Images for direct image URLs with dimensions, thumbnails, and source pages. Price: $0.015 |
| search_places | Search local businesses via Google Local: names, addresses, ratings, reviews, phone, website, coordinates. Price: $0.045 |
| search_shopping | Search Google Shopping for products with prices, sellers, ratings, and links. Price: $0.015 |
| search_scholar | Search Google Scholar for academic papers with snippets, publication info, and citation counts. Price: $0.015 |
| search_autocomplete | Get Google Autocomplete suggestions for a partial query — keyword research and intent discovery. Price: $0.015 |
| search_trends | Get Google Trends interest-over-time timeline for a query. Price: $0.015 |
| youtube_transcript | Get the full transcript of a YouTube video with timestamps. Accepts a video ID or any YouTube URL. Price: $0.03 |
| get_contents | Fetch 1-20 URLs and get clean markdown per page, truncated to a character cap. Price: $0.0015/URL |
| answer_question | Get a grounded answer with inline [n] citations: searches the web, fetches sources, and answers strictly from them. Price: $0.05 |
| extract_data | Extract structured data from a webpage using a JSON schema. AI-powered extraction. Price: $0.03 |
| smart_extract | Extract data using natural language. AI understands what you want. Price: $0.035 |
| research | One-stop research: searches web, fetches top results, and summarizes findings. Price: $0.08 |
| deep_research | 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) |
| extract_pdf | Extract text and metadata from a PDF document. Price: $0.004 |
| compare_urls | Compare 2-3 webpages and get AI-generated analysis of differences. Price: $0.05 |
| batch_fetch | Fetch multiple URLs in parallel. Efficient for bulk operations. Price: $0.0015/URL |
| domain_intel | 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 |
| project_due_diligence | 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 |
| package_intel | 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 |
| detect_tech | 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 |
| search_discussions | 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 |
| map_site | 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 |
| crawl_site | 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 |
| fetch_resilient | Resilient fetch with automatic fallback: native scraper first, then headless Chromium for JS-rendered or bot-walled pages. Price: $0.008 |
| intel_company | Company intelligence deep dive: tech stack, funding, team, competitors, news. Price: $1.00 |
| intel_market | AI-powered market research report with trends, key players, and data points. Price: $5.00 |
| intel_competitive | Competitive analysis: feature matrix, pricing, SWOT analysis. Price: $8.00 |
| intel_site_audit | Comprehensive SEO, performance, and security audit with scoring. Price: $0.75 |
| monitor_create | Create a URL change detection monitor with webhook notifications. Price: $0.01 |
| memory_set | Store key-value data in persistent agent memory. Price: $0.001 |