Kanto Labs

Model Context Protocol

Kanto Labs MCP server

Give Claude, Cursor, VS Code Copilot and any other MCP client seven web and media tools: tech stack detection, document to Markdown, SEO audit, OCR, domain lookup, video frames and bulk images.

Free, open source (MIT)You pay only the tool's per-result price
GitHub · coming soon npm: kanto-labs-mcp · coming soon

Publishing soon. The npm package kanto-labs-mcp and its GitHub repository are being published. The install commands below are final and will work as soon as the package is live.

How billing works

No Kanto Labs account. Your Apify token, your cap.

Each tool call runs the matching actor on Apify with your own Apify API token, so the actor's pay-per-result price is billed to your Apify account (Apify's free plan includes monthly credit). There is no Kanto Labs account, key or subscription.

Every call carries a spending cap, maxTotalChargeUsd (default $1.00; change it with KANTO_MAX_CHARGE_USD or per call). Apify stops the run once it has charged that much, and each result states what the call cost. Failed or unreachable inputs are not charged.

Example prompts

Just ask

  • “What is stripe.com built with? And shopify.com?”
  • “Convert https://arxiv.org/pdf/1706.03762 to Markdown and summarize section 3.”
  • “Audit the SEO of https://example.com and list the three most important fixes.”
  • “Read the text on this receipt: https://example.com/receipt.jpg. What is the total?”
  • “When do stripe.com and shopify.com expire, who is their registrar, and do they have DMARC set up?”

Setup

Install in your client

  1. Get an Apify API token: sign up at apify.com, then Settings → API & Integrations.
  2. Add the server to your client with one of the snippets below. Node.js 18.17+ is required; npx downloads the server on first run.

Claude Code

Terminal
claude mcp add kanto-labs -e APIFY_TOKEN=apify_api_your_token_here -- npx -y kanto-labs-mcp

Claude Desktop

Settings → Developer → Edit Config, then add:

claude_desktop_config.json
{
  "mcpServers": {
    "kanto-labs": {
      "command": "npx",
      "args": ["-y", "kanto-labs-mcp"],
      "env": { "APIFY_TOKEN": "apify_api_your_token_here" }
    }
  }
}

Cursor

~/.cursor/mcp.json (global) or .cursor/mcp.json (project): the same JSON as Claude Desktop.

.cursor/mcp.json
{
  "mcpServers": {
    "kanto-labs": {
      "command": "npx",
      "args": ["-y", "kanto-labs-mcp"],
      "env": { "APIFY_TOKEN": "apify_api_your_token_here" }
    }
  }
}

VS Code (GitHub Copilot agent mode)

The token is asked for once and stored securely.

.vscode/mcp.json
{
  "inputs": [
    { "type": "promptString", "id": "apify_token", "description": "Apify API token", "password": true }
  ],
  "servers": {
    "kanto-labs": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "kanto-labs-mcp"],
      "env": { "APIFY_TOKEN": "${input:apify_token}" }
    }
  }
}

Windsurf, Cline, Zed and others: any client that launches stdio servers works: command npx, args -y kanto-labs-mcp, env APIFY_TOKEN.

Windows: if your client reports spawn npx ENOENT, use "command": "cmd" with "args": ["/c", "npx", "-y", "kanto-labs-mcp"].

Tools

What the server exposes

MCP tools and prices
ToolWhat it doesPrice
detect_website_tech_stackTechnologies a website runs on$0.003 per website
convert_document_to_markdownDocuments from a URL to clean Markdown$0.004 per document
audit_website_seoOn-page SEO score and prioritized issues$0.004 per page
extract_text_from_imageOCR for images and scanned PDFs$0.003 per image or page ($0.008 accurate)
lookup_domainRDAP/WHOIS, DNS, SSL and email security$0.003 per domain
extract_video_framesFrames from video files (coming soon)$0.002 per frame
download_imagesEvery image from pages or links (coming soon)$0.002 per image

Until the video frame and image downloader actors are public on the Apify Store, calls to those two tools return an “actor not found” error and nothing is charged.

Privacy

The server runs on your machine and talks only to api.apify.com. Your token is sent only to Apify and is never logged.