mcpbeat

webclaw MCP Server

io.github.0xMassi/webclaw
local only

webclaw runs on your own machine — the client starts it, so there is no endpoint to ping. 116 installs a week from npm.

Turn any URL into clean markdown/JSON for AI agents. Self-hostable web content extraction.

Installs per day peak 354 · avg 20 · -77% w/w
a month agotoday
116
Installs / week
npm · @webclaw/mcp
—
Stars
on GitHub
—
Last commit
0 releases in 90 days
—
License
language unknown

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add webclaw -- npx -y @webclaw/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "webclaw": {
      "args": [
        "-y",
        "@webclaw/mcp"
      ],
      "command": "npx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.webclaw]
command = "npx"
args = ["-y", "@webclaw/mcp"]
.cursor/mcp.json
{
  "mcpServers": {
    "webclaw": {
      "args": [
        "-y",
        "@webclaw/mcp"
      ],
      "command": "npx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "webclaw": {
      "args": [
        "-y",
        "@webclaw/mcp"
      ],
      "command": "npx"
    }
  }
}

webclaw — questions

Answers built from our own checks of this server.

Why is there no uptime for webclaw?
webclaw runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @webclaw/mcp was installed 116 times last week.
How do I connect webclaw?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls @webclaw/mcp straight from npm; nothing to host, nothing to sign up for.
How many people use webclaw?
The npm package @webclaw/mcp was installed 116 times in the last week. Week over week that is -77%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.