WebLens is an MCP server with 36 tools an agent can call, among them answer_question, batch_fetch, compare_urls. It answers at https://api.weblens.dev/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
Scrape, crawl, map and extract the web. Pay per call in USDC, no account or API key.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
answer_question | Get a grounded answer with inline [n] citations: searches the web, fetches sources, and answers strictly from them. Price: $0.05 Inputs: query, sources |
batch_fetch | Fetch multiple URLs in parallel. Efficient for bulk operations. Price: $0.0015/URL Inputs: urls |
compare_urls | Compare 2-3 webpages and get AI-generated analysis of differences. Price: $0.05 Inputs: urls, focus |
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 requ Inputs: url, limit, maxDepth, include, exclude, respectRobots |
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 decom Inputs: query, depth |
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 competitiv Inputs: 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, A Inputs: domain |
extract_data | Extract structured data from a webpage using a JSON schema. AI-powered extraction. Price: $0.03 Inputs: url, schema, instructions |
extract_pdf | Extract text and metadata from a PDF document. Price: $0.004 Inputs: url |
fetch_resilient | Resilient fetch with automatic fallback: native scraper first, then headless Chromium for JS-rendered or bot-walled pages. Price: $0.008 Inputs: url, timeout |
fetch_webpage | Fetch and convert a webpage to clean markdown. Fast, no JavaScript rendering. Price: $0.002 Inputs: url, timeout, cache, cacheTtl |
fetch_webpage_pro | Fetch webpage with full JavaScript rendering. Use for SPAs and dynamic content. Price: $0.006 Inputs: url, waitFor, timeout |
get_contents | Fetch 1-20 URLs and get clean markdown per page, truncated to a character cap. Price: $0.0015/URL Inputs: urls, maxChars, timeout |
intel_company | Company intelligence deep dive: tech stack, funding, team, competitors, news. Price: $1.00 Inputs: target |
intel_competitive | Competitive analysis: feature matrix, pricing, SWOT analysis. Price: $8.00 Inputs: company, maxCompetitors, focus |
intel_market | AI-powered market research report with trends, key players, and data points. Price: $5.00 Inputs: topic, depth, focus |
intel_site_audit | Comprehensive SEO, performance, and security audit with scoring. Price: $0.75 Inputs: url |
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 Inputs: url, limit, include, exclude, timeout |
memory_set | Store key-value data in persistent agent memory. Price: $0.001 Inputs: key, value, ttl |
monitor_create | Create a URL change detection monitor with webhook notifications. Price: $0.01 Inputs: url, webhookUrl |
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 si Inputs: name, registry |
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 Inputs: endpoint, url |
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 Inputs: domain, tokenAddress, chain |
research | One-stop research: searches web, fetches top results, and summarizes findings. Price: $0.08 Inputs: query, resultCount |
screenshot | Capture a screenshot of a webpage. Returns base64 PNG image. Price: $0.008 Inputs: url, width, height, fullPage |
search_autocomplete | Get Google Autocomplete suggestions for a partial query — keyword research and intent discovery. Price: $0.015 Inputs: query, limit |
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. Pri Inputs: query, limit, sort |
search_images | Search Google Images for direct image URLs with dimensions, thumbnails, and source pages. Price: $0.015 Inputs: query, limit |
search_news | Search Google News for real-time articles with source, date, and thumbnail. Price: $0.015 Inputs: query, limit |
search_places | Search local businesses via Google Local: names, addresses, ratings, reviews, phone, website, coordinates. Price: $0.045 Inputs: query, location, limit |
search_scholar | Search Google Scholar for academic papers with snippets, publication info, and citation counts. Price: $0.015 Inputs: query, limit |
search_shopping | Search Google Shopping for products with prices, sellers, ratings, and links. Price: $0.015 Inputs: query, limit |
search_trends | Get Google Trends interest-over-time timeline for a query. Price: $0.015 Inputs: query |
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 Inputs: query, limit, includeContent, contentResults, contentChars |
smart_extract | Extract data using natural language. AI understands what you want. Price: $0.035 Inputs: url, query |
youtube_transcript | Get the full transcript of a YouTube video with timestamps. Accepts a video ID or any YouTube URL. Price: $0.03 Inputs: videoId, lang |
Every block below points at https://api.weblens.dev/mcp. Pick your client and copy.
claude mcp add --transport http weblens https://api.weblens.dev/mcp
{
"mcpServers": {
"weblens": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.weblens.dev/mcp"]
}
}
}{
"mcpServers": {
"weblens": {
"url": "https://api.weblens.dev/mcp"
}
}
}{
"servers": {
"weblens": {
"type": "http",
"url": "https://api.weblens.dev/mcp"
}
}
}{
"context_servers": {
"weblens": {
"url": "https://api.weblens.dev/mcp"
}
}
}{
"mcpServers": {
"weblens": {
"serverUrl": "https://api.weblens.dev/mcp"
}
}
}{
"mcpServers": {
"weblens": {
"url": "https://api.weblens.dev/mcp"
}
}
}name: WebLens
version: 0.0.1
schema: v1
mcpServers:
- name: WebLens
type: streamable-http
url: https://api.weblens.dev/mcp{
"mcpServers": {
"weblens": {
"httpUrl": "https://api.weblens.dev/mcp"
}
}
}{
"mcpServers": {
"weblens": {
"type": "http",
"url": "https://api.weblens.dev/mcp"
}
}
}{
"mcpServers": {
"weblens": {
"url": "https://api.weblens.dev/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.weblens.dev%2Fmcp&type=streamable_http&id=weblens&name=WebLens
It answered our last check on 18 October 2026 in 366 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by weblens.dev and served from api.weblens.dev, the vendor's own domain: https://api.weblens.dev/mcp.
36, as returned by the server's own tools/list on 31 August 2026: answer_question, batch_fetch, compare_urls, crawl_site, deep_research, detect_tech, domain_intel, extract_data, and 28 more.
It answered our last check on 18 October 2026 in 366 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.weblens.dev/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: dev.weblens. Endpoint host: api.weblens.dev. ARD identifier: urn:air:dev.weblens:mcp:weblens.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.