Kreuzcrawl MCP Server

by kreuzberg-dev Your server? Claim it

local only

Kreuzcrawl runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 1 Nov 2026.

Scrape, crawl, and map websites to Markdown or JSON via local CLI.

—

Installs / week

not published

195

Stars

2 open issues

1 Nov 2026

Last commit

from GitHub

MIT

License

Rust

What changed 1

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 9 August 2026. No other catalogue keeps this.

9 Aug the owner changed

What the code does

We read the source, 17 min ago · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command cli-proxy/npm/bin/crawlberg.js:58, test_apps/node/globalSetup.ts:37, test_apps/wasm/globalSetup.ts:37

    const result = spawnSync(binPath, process.argv.slice(2), { stdio: "inherit" });

Runs an external command cli-proxy/pypi/crawlberg_cli/downloader.py:263

    completed = subprocess.run([binary_path, *args], check=False)

Builds a file path from a variable packages/go/cmd/install/main.go:138, plugin/.opencode/ai-rulez-content.js:28, packages/go/cmd/setup/main.go:208

    libDir := filepath.Join(targetDir, "lib", goDir)

Includes a file named by a variable test_apps/php/bootstrap.php:24

    require_once $pkgAutoloader;

Runs an external command test_apps/csharp/TestSetup.cs:134

        _mockServer = Process.Start(psi)

Runs an external command test_apps/php/bootstrap.php:38

    $proc = proc_open([$mockServerBin, $fixturesDir], $descriptors, $pipes);

Runs an external command packages/dart/lib/src/native_loader.dart:250

    final result = await Process.run('tar', [

Touches key and credential files .alef-ownership.toml:4282

  "e2e/node/.npmrc",

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Alternatives to Kreuzcrawl

same job, measured the same way

Crawlberg

by xberg-io

Scrape, crawl, and map websites to Markdown or JSON via local CLI.

local only

SnoopScan

by snoopscan

Web scraping for agents: scrape, crawl, map, search and extract pages as clean markdown or JSON.

34 tools answering

WebReaper

by alex-on-ai

AI-native web scraper: scrape, crawl and map any site to clean markdown over stdio. MIT-licensed.

local only

CRW Web Scraper

by fastcrw

Open-source web scraper for AI agents with scrape, crawl, and map tools

local only

CRW Web Scraper

by us

Open-source web scraper for AI agents with scrape, crawl, and map tools

local only

switch402

by switch402

Markdown scrape, site map, page metadata, screenshots, web search and PDF to text. Pay per call

9 tools answering

WebLens

by weblens

Scrape, crawl, map and extract the web. Pay per call in USDC, no account or API key.

26 tools answering

Metalift

by metalift-ai

Metalift MCP for AI agents: web search (2 credits), scrape, crawl, and map tools

70 installs/wk local only

Kreuzcrawl — questions

Answers built from our own checks of this server.

Why is there no uptime for Kreuzcrawl?

Kreuzcrawl runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone.

Is Kreuzcrawl open source?

Yes — it is published under the MIT licence, written in Rust, 195 stars on GitHub and 2 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.