MCP.Market

Tollkit MCP server

online · 100% uptime
by UltraStarz·io.github.UltraStarz/x402-extract·v0.9.1

Web search, pages and PDFs, crypto market data, SEC filings and weather for agents. USDC per call.

B76/100grade B
What users say
No reviews yet
Be the first
Safety scan
B76/100

not scanned yet

Adoption
Growing

0 stars

Reviews

Write one

Nobody has reviewed Tollkit yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Tollkit tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Not scanned yet. New listings are scanned within a day or two of arriving.

How Tollkit compares

Against every graded Scraping and browsing MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
76/100
higher than 43% of 867 Scraping and browsing servers
Uptime
100%
of our recent checks; the typical remote Scraping and browsing server answers 100%
Response time
205 ms
faster than 56% of 385 Scraping and browsing servers

Release history: 7 versions in the registry since 2026-05-10, latest 2026-10-21, typically one every 11 days.

Install Tollkit in Claude Code, Cursor or VS Code

claude mcp add --transport http x402-extract https://api.tollkit.dev/mcp
Add to Cursor

What the publisher says

From the Tollkit repository's README, as published. We do not edit it. Read it on GitHub

x402-extract-mcp

A paid MCP server that gives AI agents structured product data from any URL.

Each extract_product tool call:

  1. Renders the URL through a headless browser
  2. Extracts a schema.org/Product JSON blob (name, price, currency, availability, variants, …)
  3. Costs $0.01 USDC per call, paid automatically from the configured wallet via x402

No API keys. No subscription. The agent pays the toll, gets the data.

Install in Claude Desktop / Cursor / Windsurf

Add this to your MCP config (~/Library/Application Support/Claude/claudedesktopconfig.json on macOS):

{
  "mcpServers": {
    "x402-extract": {
      "command": "npx",
      "args": ["-y", "x402-extract-mcp"],
      "env": {
        "BUYER_PRIVATE_KEY": "0xYOUR_PRIVATE_KEY"
      }
    }
  }
}

Restart your MCP client. You'll see an extract_product tool available.

What you need

A wallet on Base Sepolia (testnet) funded with:

  • A small amount of ETH for gas (free from )
  • USDC for payments (free from , select Base Sepolia)

Generate a throwaway key:

node -e "const {generatePrivateKey,privateKeyToAccount}=require('viem/accounts');const k=generatePrivateKey();console.log('PRIVATE_KEY=',k);console.log('ADDRESS=',privateKeyToAccount(k).address)"

Use the printed address to claim from faucets, then put the printed key into your MCP config.

Try it

In Claude Desktop, paste a product URL and ask:

Extract this product page using extract_product: https://stormkeep-odl.bandcamp.com/album/the-nocturnes-of-iswylm-2

You'll get back structured JSON with the product name, price, formats, availability, etc. The on-chain transfer is visible at .

What the response looks like

{
  "product": {
    "name": "The Nocturnes Of Iswylm",
    "description": "...",
    "brand": "Stormkeep",
    "price": 10,
    "currency": "USD",
    "availability": "preorder",
    "variants": [
      { "name": "Format", "values": ["Digital Album", "12\" Vinyl (black)", ...] },
      { "name": "Vinyl Color", "values": ["Black", "Violet", ...] }
    ],
    "images": [],
    "url": "https://..."
  },
  "page": { "title": "...", "status": 200, "render_ms": 2879 },
  "extraction": { "model": "claude-haiku-4-5", "input_tokens": 4479, "output_tokens": 405 }
}

Configuration

To point the MCP server at your own seller deployment, override EXTRACT_URL.

How it works

Claude Desktop ──tool call──> MCP server (this package, on your machine)
                              │
                              │ x402 payment + URL
                              ▼
                              Public seller (Hono + Playwright + Claude on Railway)
                              │
                              │ structured JSON
                              ▼
                              MCP server ──tool result──> Claude Desktop

The MCP server doesn't render pages itself. It signs an x402 payment with the buyer's wallet, sends the payment + URL to a public seller endpoint, and returns the seller's response. The seller does the actual headless rendering and Claude-driven schema extraction.

What works, what doesn't

Works well:

  • Bandcamp release pages
  • Most small/medium Shopify stores
  • Tesla Shop product pages
  • Any site that doesn't have aggressive anti-bot

Will return a fetch error (page status 403/429/no-content):

  • Amazon, Walmart, Target, Best Buy
  • Most luxury brand sites on Cloudflare
  • LinkedIn, Twitter/X (auth wall)

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-10-16downgradeA → Bscore 76: Write-action tools reachable without authentication; Unusually long tool description (over 2,000 characters)

Tollkit: common questions

Is Tollkit MCP server safe?
Mostly: it is graded B (76/100). Read the Tollkit safety report
How do I install Tollkit?
It runs remotely at api.tollkit.dev. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Tollkit need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Tollkit maintained?
The last commit was 30 days ago (2026-10-07). The latest release is v0.9.1.
Is Tollkit up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Tollkit?
Servers from other publishers that do the same job: Open Agent Search MCP server, Rendex: Rendering API for Images, PDFs & Content Extraction MCP server and AIHawk MCP server.
How does Tollkit compare with other Scraping and browsing MCP servers?
safety score 76/100 (higher than 43% of 867 Scraping and browsing servers); uptime 100% (of our recent checks; the typical remote Scraping and browsing server answers 100%); response time 205 ms (faster than 56% of 385 Scraping and browsing servers). Full comparison.

Alternatives to Tollkit

Same job from other publishers: the closest match first, then the best rated.

  • Open Agent Search
    Search the web, news, images, videos and books, and extract page content for AI agents.
    A
  • Rendex: Rendering API for Images, PDFs & Content Extraction
    Render HTML, Markdown, or URLs to images, PDF, or branded artifacts; extract and watch pages.
    A
  • AIHawk
    AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.
    A
  • Brightdata
    Bright Data's Web MCP server enabling AI agents to search, extract & navigate the web
    B
  • Browser Use
    Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
    A

More from UltraStarz →