Skip to content
MCP server

webclaw

Scrape, crawl, search and extract web pages as clean Markdown or JSON for agents

Pricing
Freemium
Platforms
CLI, API, self-hosted
Runs
Locally or Remotely
Version
0.7.1
Listing updated
3 days ago

About webclaw

webclaw is a freemium MCP server for web search and scraping. It can run locally on your machine or as a hosted remote server.

Pages are reduced to the text a model needs: navigation, scripts and boilerplate are stripped, and output can be Markdown, JSON, plain text or raw HTML, with structured extraction and an LLM mode. Beyond HTML, the API handles PDFs and DOCX files, and attempts JavaScript rendering and protected-page handling, though upstream restrictions can still block extraction.

There are two ways in. A local stdio server offers 14 tools inside Claude, Cursor, Windsurf, Codex and other clients, with an optional WEBCLAW_API_KEY enabling cloud fallback for bot-protected pages. A hosted remote endpoint serves the same job through the paid API.

The core is Rust under AGPL-3.0 and can be self-hosted; the hosted API bills one credit per page from a pool, with research counted in separate monthly runs. Routes compatible with Firecrawl's /v2/scrape, /v2/crawl and /v2/search can ease migration.

Install

Run in a terminal

claude mcp add --transport http webclaw https://api.webclaw.io/mcp

Add to Settings → Connectors → Add custom connector

https://api.webclaw.io/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "webclaw": {
      "url": "https://api.webclaw.io/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "webclaw": {
      "type": "http",
      "url": "https://api.webclaw.io/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "webclaw": {
      "serverUrl": "https://api.webclaw.io/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "webclaw": {
      "type": "http",
      "url": "https://api.webclaw.io/mcp"
    }
  }
}

Configuration

  • WEBCLAW_API_KEYOptional Webclaw API key. Enables cloud fallback for bot-protected and JavaScript-heavy pages.

What it does

Clean output
Markdown, JSON, text or HTML without page clutter.
Structured extraction
Request the fields your application needs.
Crawl and search
Crawl sites and run searches through one API.
Research runs
Deep research metered separately from credits.
Self-hostable
AGPL-3.0 Rust core with CLI, REST server and MCP server.
Firecrawl-style routes
Compatible /v2 scrape, crawl and search routes.

Good for

  • Feed clean Markdown into a RAG pipeline
  • Give an agent live web content with source URLs
  • Watch prices or stock on a page
  • Run deep research from an assistant

Pricing

Freemium, from $19 a month

Self-host free (AGPL-3.0); hosted Starter $19/mo, Growth $49, Pro $99, Scale $399

Prices change. Check webclaw.io before you buy.

webclaw FAQ

How many tools does the local server have?

14.

Can I self-host?

Yes, the open-source core is AGPL-3.0 and runs on your own hardware without hosted credits.

What do hosted plans cost?

From $19 a month for 5,000 credits, up to $399 a month for 500,000.

Is there a trial?

A 7-day trial with a card required, cancel anytime.

Is webclaw free?

webclaw has a free plan, with paid plans for more usage or features. Paid plans start at $19 a month.

How do I add webclaw to Claude Code?

Run this command in your terminal: claude mcp add --transport http webclaw https://api.webclaw.io/mcp

What are the best alternatives to webclaw?

The closest alternatives to webclaw are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and AI-Powered directory.

Alternatives to webclaw

  1. MCP server for AI clients to scrape sites with HTTP and stealth browser sessions

    Runs locally
    • 17 tools
    • Open source
    • 104K GitHub stars
    • Web search and scraping
  2. MCP server that lets AI agents search, scrape and interact with web pages

    • 3 tools
    • Remote
    • Freemium
    • 7.8K GitHub stars
    • Web search and scraping
  3. SearXNG Search

    MCP server

    MCP server for web search and page reading through a SearXNG instance

    Runs locally
    • 3 tools
    • Open source
    • 1.4K GitHub stars
    • Web search and scraping
  4. NeuralVerge

    MCP server

    Structured, source-tagged business and people data from 300+ sources for agents

    • 200 tools
    • Remote
    • Free trial
    • 1 GitHub star
    • Web search and scraping
  5. Search AI tools, agents and MCP servers and get install configs from inside your AI assistant.

    • 4 tools
    • Remote
    • Free
    • Developer tools
  6. Hosted MCP server that returns any Shopify store's products, prices and stock

    Not checked yet
    • 4 tools
    • Remote
    • Paid
    • E-commerce