# Webclaw (MCP server)

> Webclaw is an MCP server that adds web browsing tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Fast, local-first web content extraction for LLMs. It has 2,369 GitHub stars, is released under the AGPL-3.0 license and runs locally with npx -y @webclaw/mcp.

Turn websites into clean markdown, JSON, and LLM-ready context. CLI, MCP server, REST API, and SDKs for AI agents and RAG pipelines.

## Key facts

| Fact | Value |
|---|---|
| Repository | https://github.com/0xMassi/webclaw |
| GitHub stars | 2,369 |
| License | AGPL-3.0 |
| Language | Rust |
| Transport | stdio |
| Packages | npm: @webclaw/mcp; docker: ghcr.io/0xmassi/webclaw |
| Remote URL | none |
| Needs API key | no |
| Official | no |
| Works with | Claude Desktop, Claude Code, Cursor, VS Code |
| Category | Web & browsing |
| Latest release | v0.6.23 (Sep 14, 2026) |
| Last commit | Sep 23, 2026 |

## Install

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "webclaw": {
      "command": "npx",
      "args": [
        "-y",
        "@webclaw/mcp"
      ]
    }
  }
}
```

Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.

### Claude Code

```sh
claude mcp add --transport stdio webclaw -- npx -y @webclaw/mcp
```

### Cursor (.cursor/mcp.json)

```json
{
  "mcpServers": {
    "webclaw": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@webclaw/mcp"
      ]
    }
  }
}
```

Project file; use ~/.cursor/mcp.json to enable it in every project.

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "webclaw": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@webclaw/mcp"
      ]
    }
  }
}
```

Config formats checked against the official docs on 2026-10-07.

## Tools

- `scrape`: Extract one URL as markdown, text, JSON, LLM format, or HTML
- `crawl`: Follow same-origin links and extract discovered pages
- `batch`: Scrape multiple URLs in parallel
- `extract`: Convert page content into structured data
- `summarize`: Summarize a page
- `diff`: Compare page content snapshots
- `brand`: Extract colors, fonts, logos, and metadata
- `search`: Search the web and scrape results
- `research`: Multi-source research workflow

## Similar MCP servers

- [Browser Use](https://appsgit.com/mcp-servers/browser-use): Control a real Chrome browser to complete any task: fill forms, extract data, book flights. (117,307 stars, MIT, official)
- [Scrapling MCP Server](https://appsgit.com/mcp-servers/scrapling-mcp-server): Web scraping with stealth HTTP, real browsers, and Cloudflare bypass. (86,017 stars, BSD-3-Clause)
- [Chrome DevTools MCP](https://appsgit.com/mcp-servers/chrome-devtools-mcp): MCP server for Chrome DevTools. (53,049 stars, Apache-2.0)
- [Bytedance Browser](https://appsgit.com/mcp-servers/bytedance-browser): MCP server for browser use access. (39,206 stars, Apache-2.0)
- [Bytedance Commands](https://appsgit.com/mcp-servers/bytedance-commands): An MCP server to run arbitrary commands. (39,206 stars, Apache-2.0)
- [Bytedance Search](https://appsgit.com/mcp-servers/bytedance-search): MCP server for web search operations. (39,206 stars, Apache-2.0)

---

Canonical page: https://appsgit.com/mcp-servers/webclaw
Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed nightly.
Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.