# WebLens (remote · api.weblens.dev)

Scrape, crawl, map and extract the web. Pay per call in USDC, no account or API key.

- Trust score: 62/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-07

## Components

- remote · `api.weblens.dev`: 62/100 (this document), [markdown](https://verifymcp.io/servers/dev-weblens-weblens/api.md), [page](https://verifymcp.io/servers/dev-weblens-weblens/api)

## Channel facts

- Endpoint: `https://api.weblens.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `2.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-07.

- **Endpoint Security**: 54/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 36 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS not yet verified: we couldn't determine whether a plaintext access path exists.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 3124 tokens (~86/item across 36 items; 36 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http dev-weblens-weblens https://api.weblens.dev/mcp
```

### Codex

```toml
[mcp_servers.dev-weblens-weblens]
url = "https://api.weblens.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-weblens-weblens": {
      "type": "remote",
      "url": "https://api.weblens.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-weblens-weblens --url https://api.weblens.dev/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-weblens-weblens:
    url: "https://api.weblens.dev/mcp"
```

### Other

```json
{
  "mcpServers": {
    "dev-weblens-weblens": {
      "type": "http",
      "url": "https://api.weblens.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-07 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-06 (score 61, +1)

- [functional] Schema quality: good → excellent
- [functional] New tool “project_due_diligence”

### 2026-08-05 (score 60, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-08-04 (score 60)

First indexed and scored.

## MCP tools (36)

### `preview_endpoint` (~149 tokens)

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

Input parameters:

- `endpoint` (string, required): Paid endpoint path to preview, e.g. "/answer"
- `url` (string): Fetch-backed endpoints only (/fetch/basic, /contents, /map): run a real truncated preview of this URL

### `fetch_webpage` (~100 tokens)

Fetch and convert a webpage to clean markdown. Fast, no JavaScript rendering. Price: $0.002

Input parameters:

- `cache` (boolean): Serve from cache when available (default true; cached responses cost 70% less)
- `cacheTtl` (number): Cache TTL in seconds (default 3600)
- `timeout` (number): Request timeout in ms (default 10000)
- `url` (string, required): The URL to fetch

### `fetch_webpage_pro` (~82 tokens)

Fetch webpage with full JavaScript rendering. Use for SPAs and dynamic content. Price: $0.006

Input parameters:

- `timeout` (number): Request timeout in ms (default 15000)
- `url` (string, required): The URL to fetch
- `waitFor` (string): CSS selector to wait for before capturing content (e.g. ".content")

### `screenshot` (~79 tokens)

Capture a screenshot of a webpage. Returns base64 PNG image. Price: $0.008

Input parameters:

- `fullPage` (boolean): Capture full page scroll
- `height` (number): Viewport height (default 720)
- `url` (string, required): The URL to screenshot
- `width` (number): Viewport width (default 1280)

### `search_web` (~135 tokens)

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

Input parameters:

- `contentChars` (number): Per-page content character cap (default 8000)
- `contentResults` (number): How many top results to fetch content for (1-10, default: 5)
- `includeContent` (boolean): Also fetch top result pages as markdown (+$0.0015/result)
- `limit` (number): Number of results (default: 10)
- `query` (string, required): Search query

### `search_news` (~60 tokens)

Search Google News for real-time articles with source, date, and thumbnail. Price: $0.015

Input parameters:

- `limit` (number): Number of results (default: 10, max: 20)
- `query` (string, required): News search query

### `search_images` (~61 tokens)

Search Google Images for direct image URLs with dimensions, thumbnails, and source pages. Price: $0.015

Input parameters:

- `limit` (number): Number of results (default: 10, max: 20)
- `query` (string, required): Image search query

### `search_places` (~92 tokens)

Search local businesses via Google Local: names, addresses, ratings, reviews, phone, website, coordinates. Price: $0.045

Input parameters:

- `limit` (number): Number of results (default: 10, max: 20)
- `location` (string): Free-text location bias, e.g. "Austin, Texas"
- `query` (string, required): What to search for (e.g. coffee shops)

### `search_shopping` (~61 tokens)

Search Google Shopping for products with prices, sellers, ratings, and links. Price: $0.015

Input parameters:

- `limit` (number): Number of results (default: 10, max: 20)
- `query` (string, required): Product search query

### `search_scholar` (~63 tokens)

Search Google Scholar for academic papers with snippets, publication info, and citation counts. Price: $0.015

Input parameters:

- `limit` (number): Number of results (default: 10, max: 20)
- `query` (string, required): Academic search query

### `search_autocomplete` (~62 tokens)

Get Google Autocomplete suggestions for a partial query — keyword research and intent discovery. Price: $0.015

Input parameters:

- `limit` (number): Max suggestions (default: 10, max: 20)
- `query` (string, required): Partial query to complete

### `search_trends` (~40 tokens)

Get Google Trends interest-over-time timeline for a query. Price: $0.015

Input parameters:

- `query` (string, required): Topic to get trend data for

### `youtube_transcript` (~86 tokens)

Get the full transcript of a YouTube video with timestamps. Accepts a video ID or any YouTube URL. Price: $0.03

Input parameters:

- `lang` (string): Transcript language code (default: video default)
- `videoId` (string, required): YouTube video ID (e.g. dQw4w9WgXcQ) or full video URL

### `get_contents` (~87 tokens)

Fetch 1-20 URLs and get clean markdown per page, truncated to a character cap. Price: $0.0015/URL

Input parameters:

- `maxChars` (number): Per-page content character cap (default 20000)
- `timeout` (number): Per-URL timeout in ms (default 10000)
- `urls` (array, required): URLs to fetch (1-20)

### `answer_question` (~76 tokens)

Get a grounded answer with inline [n] citations: searches the web, fetches sources, and answers strictly from them. Price: $0.05

Input parameters:

- `query` (string, required): The question to answer
- `sources` (number): Web sources to search, fetch, and cite (1-5, default: 3)

### `extract_data` (~70 tokens)

Extract structured data from a webpage using a JSON schema. AI-powered extraction. Price: $0.03

Input parameters:

- `instructions` (string): Natural language instructions to guide extraction
- `schema` (object, required): JSON schema defining the data structure to extract
- `url` (string, required): The URL to extract from

### `smart_extract` (~53 tokens)

Extract data using natural language. AI understands what you want. Price: $0.035

Input parameters:

- `query` (string, required): What data to extract (natural language)
- `url` (string, required): The URL to extract from

### `research` (~59 tokens)

One-stop research: searches web, fetches top results, and summarizes findings. Price: $0.08

Input parameters:

- `query` (string, required): Research topic or question
- `resultCount` (number): Number of sources to analyze (default: 5)

### `deep_research` (~189 tokens)

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)

Input parameters:

- `depth` (string): Research tier: standard = 3 sub-questions / 8 sources ($0.20); deep = 5 / 12 ($0.35). Default: standard
- `query` (string, required): The research question (1-500 chars)

### `extract_pdf` (~37 tokens)

Extract text and metadata from a PDF document. Price: $0.004

Input parameters:

- `url` (string, required): URL of the PDF to extract

### `compare_urls` (~55 tokens)

Compare 2-3 webpages and get AI-generated analysis of differences. Price: $0.05

Input parameters:

- `focus` (string): What to focus comparison on
- `urls` (array, required): URLs to compare (2-3)

### `batch_fetch` (~43 tokens)

Fetch multiple URLs in parallel. Efficient for bulk operations. Price: $0.0015/URL

Input parameters:

- `urls` (array, required): URLs to fetch (2-20)

### `domain_intel` (~136 tokens)

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

Input parameters:

- `domain` (string, required): Domain to inspect, e.g. "stripe.com". A full URL is reduced to its hostname.

### `project_due_diligence` (~174 tokens)

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

Input parameters:

- `chain` (string): Optional chain label, e.g. base, ethereum, solana
- `domain` (string, required): Project website, e.g. "example.org"
- `tokenAddress` (string): Optional contract address to cross-check against the site

### `package_intel` (~125 tokens)

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

Input parameters:

- `name` (string, required): Package name, e.g. "express" or "@scope/pkg"
- `registry` (string): Registry to look in (default npm)

### `detect_tech` (~86 tokens)

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

Input parameters:

- `url` (string, required): Site URL to fingerprint

### `search_discussions` (~100 tokens)

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

Input parameters:

- `limit` (number): Stories to return (default 10)
- `query` (string, required): What to search Hacker News for
- `sort` (string): Ranking (default relevance)

### `map_site` (~130 tokens)

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

Input parameters:

- `exclude` (array): Skip URLs whose path+query contains one of these substrings
- `include` (array): Only URLs whose path+query contains one of these substrings
- `limit` (number): Maximum URLs to return (1-5000, default: 1000)
- `timeout` (number): Timeout in ms (default 10000)
- `url` (string, required): Site URL to map

### `crawl_site` (~231 tokens)

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

Input parameters:

- `exclude` (array): Skip URLs whose path+query contains one of these substrings
- `include` (array): Only crawl URLs whose path+query contains one of these substrings
- `limit` (number): Page budget (1-25, default: 10) — charged per requested page
- `maxChars` (number): Per-page content character cap (default 8000)
- `maxDepth` (number): Link depth from the start URL (0-3, default: 2)
- `respectRobots` (boolean): Honour robots.txt (default: true; disable only for sites you control)
- `timeout` (number): Per-page timeout in ms (default 10000)
- `url` (string, required): Start URL — the crawl stays on this host

### `fetch_resilient` (~69 tokens)

Resilient fetch with automatic fallback: native scraper first, then headless Chromium for JS-rendered or bot-walled pages. Price: $0.008

Input parameters:

- `timeout` (number): Timeout in ms (default 10000)
- `url` (string, required): The URL to fetch

### `intel_company` (~44 tokens)

Company intelligence deep dive: tech stack, funding, team, competitors, news. Price: $1.00

Input parameters:

- `target` (string, required): Company name or domain to research

### `intel_market` (~65 tokens)

AI-powered market research report with trends, key players, and data points. Price: $5.00

Input parameters:

- `depth` (string): Research depth (default standard)
- `focus` (string): Optional focus area
- `topic` (string, required): Market or industry topic to research

### `intel_competitive` (~66 tokens)

Competitive analysis: feature matrix, pricing, SWOT analysis. Price: $8.00

Input parameters:

- `company` (string, required): Company to analyze
- `focus` (string): Optional focus area
- `maxCompetitors` (number): Max competitors to include (default: 5)

### `intel_site_audit` (~38 tokens)

Comprehensive SEO, performance, and security audit with scoring. Price: $0.75

Input parameters:

- `url` (string, required): URL to audit

### `monitor_create` (~51 tokens)

Create a URL change detection monitor with webhook notifications. Price: $0.01

Input parameters:

- `url` (string, required): URL to monitor for changes
- `webhookUrl` (string, required): Webhook URL for change notifications

### `memory_set` (~70 tokens)

Store key-value data in persistent agent memory. Price: $0.001

Input parameters:

- `key` (string, required): Storage key (max 256 chars)
- `ttl` (number): Time to live in hours (1-720, default: 168)
- `value` (required): Value to store (any JSON)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-weblens-weblens/api#diagnostics

## Score history

- 2026-08-07: 62
- 2026-08-06: 61
- 2026-08-05: 60
- 2026-08-04: 60

## Links

- Remote endpoint: https://api.weblens.dev/mcp
- Repository: https://github.com/vasilistotskas/weblens
- Website: https://api.weblens.dev/
- Changelog RSS feed: https://verifymcp.io/servers/dev-weblens-weblens/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-weblens-weblens/api.json
- HTML version of this page: https://verifymcp.io/servers/dev-weblens-weblens/api