Webclaw logo

Webclaw

Verified

by 0xMassi

Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API, and MCP server.

Set up this server

Compare serversMy Stack

01 / Choose your client

02 / Before you connect

Authentication is not specified. Check the project instructions before connecting.

Install the runtime required by the project and make it available to your client.

Project instructions

Use names from the project instructions, separated by commas. Enter names only, never secret values.

03 / Add the configuration

Source: generated from public install instructions

claude mcp add --transport stdio 'webclaw' -- 'npx' '-y' '@webclaw/mcp'

Run in your terminal after replacing any placeholders.

04 / Check it in your client

Open your client’s MCP settings and confirm the server connects and lists its tools. A copied configuration does not confirm a working connection.

ai-agentsai-scrapingapify-alternativeclicrawl4ai-alternativefirecrawl-alternativehtml-to-markdownjina-alternativellmmarkdownmcpmcp-serverrustscraperapi-alternativescrapingbee-alternativeself-hostedtls-fingerprintingweb-crawlerweb-extractionweb-scraping

More in Search & Web

Browse the full directory

Badge

Show this listing on your README and website

You are one of MCPVault's first 100 verified servers: verified for good, badge or no badge. Put it on your README or site if you want a live Verified proof link for visitors.

MCPVault: verifiedGet the embed code

Security profile

Exposure: Broad

Reaches into the environment, credential files or other agents' configuration.

What this server can reach, from a static read of the shipped code. Nothing was executed and nothing here is a verdict: a browser tool has to run commands and an API wrapper has to call its API. Decide what fits your setup.

NVIDIA SkillSpector v2.11.0, MCPVault MCP-server policy. Scanned yesterday @ 3c32041.

Detected

  • Talks to external services24 places

    Makes outbound requests. The hosts are listed so you can see where data goes.

    api.anthropic.com, api.atlascloud.ai, api.example.com, api.github.com, api.hetzner.cloud, api.npmjs.org, api.openai.com, api.orcarouter.ai, api.stackexchange.com, api.stripe.com, api.webclaw.io, data.census.gov, data.oecd.org, data.worldbank.org

  • Reads or writes other agents' configuration1 places

    Touches folders such as ~/.claude, ~/.codex or ~/.cursor, which hold settings and sometimes keys.

  • Accesses credential files3 places

    References SSH keys, cloud credential files or token stores.

  • Passes model output on without checks3 places

    Model output reaches HTML, SQL or a shell without validation.

  • Runs unpinned packages at runtime14 places

    Executes npx or uvx without a version, so a compromised upstream release would run.

Not detected: reads environment variables in bulk, sends conversation content outward, runs shell commands, uses elevated privileges, installs itself to run later, matches a known malicious pattern.

Dependencies with known advisories

None found in the lockfiles and manifests checked against OSV.dev.

Left out of the profile

64 pattern matches in documentation, configuration or CI files were recorded but are not part of the profile, because they do not run when the server does. The owner dashboard lists them.

How the profile works Maintainers see file, line and a fix for each item in their dashboard.
12Tools reported by the last successful handshake

10 of 10 tools · Observed tool names: 12/12

Observed tool names (12)

Reported by a complete handshake for the current saved configuration. Tools were listed, not invoked.

· 1.3.0

batchbrandcrawldiffextractlist_extractorsmapresearchscrapesearchsummarizevertical_scrape

Documented tools (10)

From project documentation. A server handshake does not verify each tool’s description or behavior.

batch

Scrape multiple URLs in parallel

brand

Extract colors, fonts, logos, and metadata

crawl

Follow same-origin links and extract discovered pages

diff

Compare page content snapshots

extract

Convert page content into structured data

map

Discover URLs without extracting every page

research

Multi-source research workflow

scrape

Extract one URL as markdown, text, JSON, LLM format, or HTML

search

Search the web and scrape results

summarize

Summarize a page

Tool change history

Compared across complete checks of the same configuration. Tools were listed, not invoked. Input-schema changes are not measured here.

  1. Sep 25, 2026, 02:22 AM UTC

    Compared with Sep 16, 2026, 02:23 AM UTC

    No tool-name changes

  2. Sep 16, 2026, 02:23 AM UTC

    Compared with Sep 9, 2026, 02:22 AM UTC

    + 0 Added

      − 2 Removed

      • lead
      • lead_batch

    FAQ

    Questions about Webclaw MCP Server

    How do I connect Webclaw MCP Server to Claude?
    Run `claude mcp add webclaw -- npx -y @webclaw/mcp` in Claude Code, or add the same command and arguments under mcpServers in Cursor's mcp.json or Claude Desktop's claude_desktop_config.json, then restart the client. The blocks above are ready to paste.
    Is Webclaw MCP Server free?
    The listed licence is AGPL-3.0. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
    What can Webclaw MCP Server do?
    Webclaw MCP Server documents 10 tools to the agent, including batch, brand, crawl. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.