kanto-labs-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| APIFY_TOKEN | No | Your Apify API token. | |
| APIFY_API_TOKEN | No | Alternative for APIFY_TOKEN. | |
| KANTO_TIMEOUT_SECS | No | Default timeout per call (max 300). Default is 280. | 280 |
| KANTO_ACTORS_CONFIG | No | Path to an alternative actors.config.json. | |
| KANTO_MAX_CHARGE_USD | No | Default spending cap per call. Default is 1.00. | 1.00 |
| KANTO_MAX_TEXT_CHARS | No | Truncate any single text field beyond this. Default is 100000. | 100000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| detect_website_tech_stackA | Detect the technologies a website runs on: CMS, ecommerce platform, JavaScript frameworks, analytics and ad tags, CDN, hosting, payment and marketing tools (7,600+ fingerprints, with versions and confidence). Use it for lead qualification, competitor research, sales prospecting or 'what is this site built with?' questions. Reads only the public page, one request per site. Cost: $0.003 per website analyzed, billed to your Apify account; failed or unreachable sites are free. Runs the Apify actor kantolabs/website-tech-stack-detector with your APIFY_TOKEN; maxTotalChargeUsd caps the spend per call. |
| convert_document_to_markdownA | Download documents from public URLs and convert them to clean Markdown: PDF, DOCX, PPTX, XLSX/XLS, CSV, EPUB, HTML, IPYNB, MSG, TXT, JSON, XML, RSS and ZIP archives of these. Returns the Markdown plus title, page and word counts, and optional heading-aware chunks for RAG / vector databases. Use it when you need to read, summarize, quote or index a document that is only reachable by link. Cost: $0.004 per document converted, billed to your Apify account; unsupported or failed files are free. Runs the Apify actor kantolabs/document-to-markdown with your APIFY_TOKEN; maxTotalChargeUsd caps the spend per call. |
| audit_website_seoA | Run an on-page SEO audit: 0-100 score and a prioritized list of issues (title, meta description, headings, canonical, indexability, structured data, Open Graph, images without alt, speed, robots.txt, sitemap, llms.txt and AI-crawler blocking), with optional broken-link checking and an internal crawl. Use it when asked to audit, review or improve a site's SEO, or to compare pages. Cost: $0.004 per page audited, billed to your Apify account; unreachable pages are free. Crawling multiplies cost: pages = urls x maxPagesPerSite at most. Runs the Apify actor kantolabs/website-seo-audit with your APIFY_TOKEN; maxTotalChargeUsd caps the spend per call. |
| extract_text_from_imageA | OCR: extract the text from images, screenshots, photos and scanned PDFs reachable by URL (PNG, JPG, WEBP, TIFF, BMP, GIF, HEIC, PDF). Returns reading-order text per image or PDF page with an average confidence, and optionally every line with its pixel bounding box. Reads English and other Latin-script languages, Chinese and Japanese; PDFs that already contain a text layer are read exactly without OCR. Use it for receipts, invoices, forms, scanned documents, screenshots and product photos when you need the words in the image, not a description of it. For digital (non-scanned) PDFs and Office files prefer convert_document_to_markdown. Cost: $0.003 per image or PDF page read ($0.008 with quality "accurate"), billed to your Apify account; failed downloads and pages with no text are free. Runs the Apify actor kantolabs/image-to-text-ocr with your APIFY_TOKEN; maxTotalChargeUsd caps the spend per call. |
| lookup_domainA | One report per domain: registration data via RDAP/WHOIS (registered or available, registrar, creation and expiry dates, domain age, status, nameservers, DNSSEC), all DNS records (A, AAAA, MX, NS, TXT, CAA, SOA, www), the SSL certificate (valid, issuer, expiry, days left, SANs, TLS version) and email security (SPF, DKIM, DMARC, MTA-STS, detected email provider, 0-100 score and A-F grade), plus a plain-English list of issues. Accepts domains, URLs or email addresses. Use it for 'who is the registrar / when does it expire / is this domain available / is the certificate valid / who hosts their email / is DMARC set up' questions, lead enrichment and domain or certificate monitoring. No registrant personal data is returned. Cost: $0.003 per domain analyzed, billed to your Apify account; invalid domains and failed lookups are free. Runs the Apify actor kantolabs/domain-whois-dns-ssl-lookup with your APIFY_TOKEN; maxTotalChargeUsd caps the spend per call. |
| extract_video_framesA | COMING SOON: this Kanto Labs actor is not public on the Apify Store yet. Until it is, calls return an 'actor not yet public' error and nothing is charged. Extract still frames from video files reachable by direct URL (MP4, MOV, WEBM, MKV, AVI, M4V, MPEG-TS; not YouTube or TikTok pages): an automatic storyboard of scene changes, scene cuts only, N evenly spaced frames, or one frame every N seconds. Returns public image URLs with timestamps for every frame, a free contact-sheet grid image, and the video's duration, resolution, fps and codecs. Use it to let a vision model 'watch' a video, to make thumbnails or storyboards, or to find scene changes. A call must finish within 300 seconds, so send one or a few short videos per call. Cost: $0.002 per frame extracted (default 12 frames per video = $0.024), billed to your Apify account; videos that fail to download or decode are free. Runs the Apify actor kantolabs/video-frame-extractor with your APIFY_TOKEN; maxTotalChargeUsd caps the spend per call. |
| download_imagesA | COMING SOON: this Kanto Labs actor is not public on the Apify Store yet. Until it is, calls return an 'actor not yet public' error and nothing is charged. Download every image from web pages (img tags, srcset, lazy-load attributes, CSS backgrounds, optionally favicons and SVGs) and/or from direct image links, with size and format filters, de-duplication and optional conversion or resizing. Each saved image gets a public download URL plus its dimensions, format, alt text and SHA-256. Use it to collect product photos, gallery or article images, or to re-host and convert a list of image links. Only for images you have the right to use; social networks and stock-photo sites are refused. Cost: $0.002 per image saved, billed to your Apify account; duplicates, filtered-out and failed images are free. A page can hold hundreds of images, so set maxImagesPerPage and minWidth to control cost. Runs the Apify actor kantolabs/bulk-image-downloader with your APIFY_TOKEN; maxTotalChargeUsd caps the spend per call. |
| check_domain_authorityA | COMING SOON: this Kanto Labs actor is not public on the Apify Store yet. Until it is, calls return an 'actor not yet public' error and nothing is charged. Score how authoritative (well linked) domains are: a 0-100 authority score computed from the open Common Crawl domain web graph of about 133 million domains, with the harmonic-centrality rank, PageRank rank, top-% percentile, number of subdomains seen, and the rank change and trend (up/down/stable/new) against the previous monthly graph. Accepts domains, URLs or email addresses; each is reduced to its registrable domain. Use it for link-building and outreach prospect lists, guest-post or PR vetting, expired-domain research, lead scoring and competitor tracking. It is its own open metric, NOT Moz Domain Authority or Ahrefs Domain Rating: compare domains against each other. It does not return backlinks and visits no website. Domains outside the top 12 million come back with ranked=false (score below 20) and are free. Thousands of domains finish in seconds. Cost: $0.001 per domain scored, billed to your Apify account; unranked and invalid domains are free. Runs the Apify actor kantolabs/domain-authority-checker with your APIFY_TOKEN; maxTotalChargeUsd caps the spend per call. |
| enrich_companyA | COMING SOON: this Kanto Labs actor is not public on the Apify Store yet. Until it is, calls return an 'actor not yet public' error and nothing is charged. Turn domains, website URLs, email addresses or company names into company profiles. From one normal visit to the company's homepage: name, description, logo and favicon URLs, brand colour, language, the company's own social profile links (LinkedIn, X, Facebook, Instagram, YouTube, GitHub...), App Store / Google Play links and key pages (about, pricing, careers, contact, blog, docs). From Wikidata (open data): industries, country, headquarters, founding date, employee count and revenue (with the year of each figure), stock tickers, parent organization, legal form and LEI. Use it for CRM or lead-list enrichment, account research before a sales call, logo walls, market maps, or 'tell me about this company' questions. Names are matched on Wikidata (well-known organizations only); pass a domain for an exact match. Small businesses usually get the website fields only. Returns no personal data (no people, emails or phone numbers). Cost: $0.003 per company enriched, billed to your Apify account; unreachable domains, unknown names and invalid inputs are free. Runs the Apify actor kantolabs/company-enrichment with your APIFY_TOKEN; maxTotalChargeUsd caps the spend per call. |
| upscale_imageA | COMING SOON: this Kanto Labs actor is not public on the Apify Store yet. Until it is, calls return an 'actor not yet public' error and nothing is charged. Enlarge images 2x or 4x with Real-ESRGAN, the open-source AI super-resolution model, run inside the actor (no third-party AI API): sharper edges and textures, less blur and JPEG noise than a normal resize. Two models: "general" for photos, product shots, screenshots and scans; "anime" for anime, cartoons, illustrations, logos and line art. Transparency is kept. Returns a public download URL for each upscaled file with input and output dimensions. Use it to make small product photos, thumbnails or artwork print- or store-ready, or to enlarge small text before OCR. Inputs up to about 0.3 megapixels (640x480) are standard price (output up to 2560x1920 at 4x); bigger inputs are reduced to that size unless allowLargeImages is true, which upscales inputs up to about 2.1 MP (1920x1080) at full size at the large price. Upscaling takes about 12 s per standard image and about 80 s per large one, and a call must finish within 300 s, so send at most about 15 standard or 3 large images per call. Only images you have the right to process; social-network and stock-photo links are refused. Cost: $0.01 per image upscaled, $0.06 per large image, billed to your Apify account; failed or refused images are free. Runs the Apify actor kantolabs/ai-image-upscaler with your APIFY_TOKEN; maxTotalChargeUsd caps the spend per call. |
| get_topic_trendsA | COMING SOON: this Kanto Labs actor is not public on the Apify Store yet. Until it is, calls return an 'actor not yet public' error and nothing is charged. Measure and compare interest in topics over time, like Google Trends, from official Wikipedia pageview data (human traffic, 2015-07-01 to yesterday, CC0). Each keyword is matched to one Wikipedia article (exact title first, else the top non-disambiguation search hit; the matched article is returned so you can check it; write "Apple Inc." for the company, "apple" gives the fruit). Per topic: a daily, weekly or monthly timeline with absolute views and a 0-100 value normalised across all keywords of the call, total and average views, peak date, latest value, change percent and trend (rising/stable/falling), spike days, and interest by language edition. Use it for 'is interest in X growing?', comparing brands, products, people or technologies, seasonality, or finding the day a story broke. It counts people reading about a topic, not Google searches, and has no per-city data. About 5-10 s for 3 keywords and about a minute for 10 keywords over 12 months, so send up to about 30 keywords per call. Cost: $0.003 per topic analyzed, billed to your Apify account; keywords with no matching article are free. Runs the Apify actor kantolabs/wikipedia-trends with your APIFY_TOKEN; maxTotalChargeUsd caps the spend per call. |
| get_trending_topicsA | COMING SOON: this Kanto Labs actor is not public on the Apify Store yet. Until it is, calls return an 'actor not yet public' error and nothing is charged. List what people are reading about on a given day: the most-read Wikipedia articles per country (US, GB, IN, DE, JP... readers in that country; views rounded up to the nearest 100 by Wikimedia) and/or per language edition (exact views), with rank, views and a one-line description. Main pages, search and special pages are removed. Data comes from the official Wikimedia Pageviews API (CC0) and is published about one day later, so the default day is the latest published one (usually yesterday). Use it for news and social monitoring, content ideas, or 'what is trending in Japan today?'. If neither trendingCountries nor trendingProjects is given, the English edition is listed. Cost: $0.0005 per trending article returned, billed to your Apify account; lists that fail or have no data yet are free. Runs the Apify actor kantolabs/wikipedia-trends with your APIFY_TOKEN; maxTotalChargeUsd caps the spend per call. |
| check_website_traffic_rankA | COMING SOON: this Kanto Labs actor is not public on the Apify Store yet. Until it is, calls return an 'actor not yet public' error and nothing is charged. How popular is a website, worldwide and by country? From published open data (Chrome UX Report popularity ranks, CC BY 4.0, and the Majestic Million, CC BY 3.0): the global Chrome popularity tier (top 1K, 5K, 10K, 50K, 100K, 500K or 1M websites), month-over-month trend, the countries where the site ranks best and its tier in each of 40 countries, plus Majestic rank, referring subnets and IPs (a backlink-strength signal) and an overall popularityTier. Use it for lead scoring, competitor and market research, vetting publishers, affiliates or link-building targets, and market sizing by country. It gives tiers, not exact positions or monthly visit counts, and does not visit the websites. Sites below the top 1M everywhere and not in the Majestic Million come back ranked=false and are free. Cost: $0.002 per domain ranked, billed to your Apify account; unranked and invalid domains are free. Runs the Apify actor kantolabs/website-traffic-rank with your APIFY_TOKEN; maxTotalChargeUsd caps the spend per call. |
| search_free_imagesA | COMING SOON: this Kanto Labs actor is not public on the Apify Store yet. Until it is, calls return an 'actor not yet public' error and nothing is charged. Find pictures you may legally reuse: searches the 100M+ freely licensed files on Wikimedia Commons through the official MediaWiki API and returns only images under free licenses that allow commercial use (public domain, CC0, CC BY, CC BY-SA...). Each image comes with the full-size original URL, a thumbnail URL, the file page, width, height, orientation, license, license family, whether attribution or share-alike is required, the author, a ready-to-paste attribution line (text and HTML), community quality marks and any extra restrictions (trademarks, personality rights). Filter by license ("noAttribution" = public domain/CC0 only, "commercialNoShareAlike" = PD/CC0/CC BY), minimum size, orientation and file type. Use it for article featured images, product or slide visuals, maps, flags, diagrams, historical photos and licensed image datasets. Works best for concrete subjects (animals, food, places, objects, events); abstract stock concepts return fewer matches, so search for the concrete scene. Not legal advice: follow each image's license. Cost: $0.001 per image returned, billed to your Apify account; filters apply before charging and a search with no match is free. Runs the Apify actor kantolabs/free-image-search with your APIFY_TOKEN; maxTotalChargeUsd caps the spend per call. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 14 tools
Each tool targets a distinct resource and action, and descriptions are detailed enough to separate them. The closest call is get_topic_trends vs get_trending_topics, which both use Wikipedia pageviews but measure different things; check_domain_authority vs check_website_traffic_rank also share a domain-ranking flavor. No two tools are truly interchangeable.
All 14 tools follow a clean verb_noun snake_case pattern (detect_website_tech_stack, upscale_image, lookup_domain). Commands use imperative verbs and the object is always a noun or noun phrase. Minor phrasing differences like convert_document_to_markdown vs download_images don't break the overall consistency.
14 tools is at the upper edge of the typical well-scoped range, and each represents a distinct utility. The set feels like a grab-bag of Kanto Labs Apify actors rather than a tightly integrated product, but none of the tools are redundant. Slightly broad, still reasonable for a general web-research and media toolkit.
Nine of the 14 tools are explicitly marked 'COMING SOON' and return an 'actor not yet public' error, leaving only five functional tools. That is a significant gap: agents will select valid-sounding tools for video, image, company, and trend tasks and hit dead ends. The available five cover website tech/SEO/domain/document/OCR well, but the server's advertised surface is largely unusable.