Webclaw vs Agent Scraper MCP

A side-by-side look at the Webclaw and Agent Scraper MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

Webclaw logoWebclawSearch & Data Extraction · Local subprocess (stdio)Web content extraction for AI agents. 10 tools: scrape, crawl, map, batch, extract, summarize, diff, brand, search, research. TLS fingerprinting bypasses anti-bot without a browser. 67% fewer tokens than raw HTML. npx create-webclaw auto-configures Claude, Cursor, Windsurf, Codex, OpenCode.69GreatAuth: no auth requiredAgent Scraper MCP logoAgent Scraper MCPSearch & Data Extraction · Local subprocess (stdio)Web scraping MCP server for AI agents. 6 tools: clean content extraction, structured scraping with CSS selectors, full-page screenshots via Playwright, link extraction, metadata extraction (OG/Twitter cards), and Google search. Free tier with x402 micropayments.59GoodAuth: other

Verdict: choose Webclaw for search & data extraction work as a local process; choose Agent Scraper MCP for search & data extraction as a local process. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Webclaw logoChoose Webclaw when

  • You need dedicated capabilities in the Search & Data Extraction domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: No auth required.
  • You want tools like scrape, select, screenshot.
Explore Webclaw

Agent Scraper MCP logoChoose Agent Scraper MCP when

  • You need dedicated capabilities in the Search & Data Extraction domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: other.
  • You have the keys it needs: PUBLIC_HOST, X402_WALLET_ADDRESS.
  • You want tools like title, description, canonical.
Explore Agent Scraper MCP

Feature & specification comparison

Rows where the two servers differ are marked.

SpecWebclaw logoWebclawAgent Scraper MCP logoAgent Scraper MCP
CategorySearch & Data ExtractionSearch & Data Extraction
Quality signal69/100 · Great59/100 · Good
Install commandConfirmedConfirmed
TransportLocal subprocess (stdio)Local subprocess (stdio)
AuthNo auth requiredother
PricingFreeFreemium
Required env varsNone listedPUBLIC_HOSTX402_WALLET_ADDRESS
Verified ownerCommunity listingCommunity listing
GitHub stars2,3888
Directory activity 13 views 2 installs 0 upvotes 5 views 0 installs 0 upvotes
Tools126

Tools & capabilities

Webclaw tools 12

  • scrapeExtract one URL as markdown, text, JSON, LLM format, or HTML
  • selectPick values or records from a page with CSS selectors or XPath, its data tables, elements found by text, or every element like an example, as JSON
  • screenshotCapture a page's viewport or the whole page as PNG or JPEG, print it to PDF, or save it as one MHTML file
  • crawlFollow same-origin links and extract discovered pages, most relevant first with a `query
  • mapDiscover URLs from sitemaps, a short crawl and the Common Crawl index without extracting every page
  • batchScrape multiple URLs in parallel
  • extractConvert page content into structured data
  • summarizeSummarize a page
  • diffCompare page content snapshots
  • brandExtract colors, fonts, logos, and metadata
  • searchSearch the web and scrape results
  • researchMulti-source research workflow

Agent Scraper MCP tools 6

  • titlePage title
  • descriptionMeta description
  • canonicalCanonical URL
  • faviconFavicon URL
  • ogOpen Graph tags
  • twitterTwitter Card tags

Ready-to-paste client configs

Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.

Webclaw

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "0xmassi-webclaw": {
      "command": "npx",
      "args": [
        "-y",
        "create-webclaw"
      ]
    }
  }
}

Agent Scraper MCP

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "aparajithn-agent-scraper-mcp": {
      "command": "uvx",
      "args": [
        "x402-fetch"
      ],
      "env": {
        "PUBLIC_HOST": "YOUR_PUBLIC_HOST_HERE",
        "X402_WALLET_ADDRESS": "YOUR_X402_WALLET_ADDRESS_HERE"
      }
    }
  }
}

Frequently asked questions

Webclaw is categorized under Search & Data Extraction and uses a local stdio subprocess. Agent Scraper MCP belongs to Search & Data Extraction and uses a local stdio subprocess. Pick Webclaw for search & data extraction work and Agent Scraper MCP for search & data extraction.

Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.

Webclaw is listed as free. Auth: no auth required. Agent Scraper MCP is listed as freemium — a free tier with paid plans. Auth: other. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.

Yes. MCP clients support multiple servers: add 0xmassi-webclaw and aparajithn-agent-scraper-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Webclaw has a quality signal of 69/100 (Great) with 13 views, 2 installs and 2,388 GitHub stars. Agent Scraper MCP has 59/100 (Good) with 5 views, 0 installs and 8 GitHub stars.