Kreuzcrawl MCP Server

Turn any website into clean, structured data. Point Crawlberg at a URL and get back Markdown, metadata, and links - from a single page or a whole site - in the language you already use.

People who need web scraping tools inside Claude, Cursor, VS Code, or another MCP client. The project is written in Rust.

VERIFIED ACTIVE

LAST COMMIT 2026-08-24 · ★ 162 · #36 OF 78 MAINTAINED WEB SCRAPING · VERIFIED 2026-08-25

MIT · Rust servers · how we verify → /methodology

01 · Install Kreuzcrawl

Docker

docker run -i --rm ghcr.io/kreuzberg-dev/kreuzcrawl:0.3.0

Claude Desktop - add to config

{
  "mcpServers": {
    "kreuzberg-dev-kreuzcrawl": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/kreuzberg-dev/kreuzcrawl:0.3.0"
      ]
    }
  }
}

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as container (OCI image) - can be sandboxed away from your filesystem

license MIT - declared in the repository

registry namespace io.github.kreuzberg-dev is GitHub-verified and matches the repo owner

03 · What Kreuzcrawl can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v1.4.0 · 2026-08-24

Added · Bounded LLM extraction concurrency (ai feature). LlmExtractor now builds a · liter_llm::ManagedClient instead of a bare DefaultClient, with liter-llm 1.18.0's queueing · InFlightLimitLayer wired in. The new…

v1.3.3 · 2026-08-22

Fixed · CI Lint's Validate (poly) job runs again. poly lint . never reached a crawlberg finding: · golangci-lint v2.12.2 (the reusable workflow's default) vendors honnef.co/go/tools v0.7.0, · whose IR builder panics…

v1.3.2 · 2026-08-21

Fixed · The release actually publishes. v1.3.1 was tagged and released but published nothing to any · the Validate versions gate failed on stale Cargo.lock files under e2e/rust, · fuzz and…

04 · Who maintains Kreuzcrawl

Kreuzcrawl is maintained by kreuzberg-dev. It's the only MCP server we track from this author; the repo dates to Mar 2026.

05 · Facts

repository: github.com/kreuzberg-dev/kreuzcrawl
website: https://kreuzberg.dev/
category: web scraping - ranked #36 of 78 actively-maintained web scraping servers as of 2026-08-25.
release cadence: 10+ releases in the last 90 days (latest 2026-08-24)
registry: io.github.kreuzberg-dev/kreuzcrawl (active, first published 2026-06-21 · 4 versions)
packages: oci:ghcr.io/kreuzberg-dev/kreuzcrawl:0.3.0

06 · Kreuzcrawl FAQ

What is Kreuzcrawl?

Turn any website into clean, structured data. Point Crawlberg at a URL and get back Markdown, metadata, and links - from a single page or a whole site - in the language you already use.

Is Kreuzcrawl still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-24 and it shipped 10+ releases in the last 90 days. We re-verify nightly.

How do I install Kreuzcrawl?

Run `docker run -i --rm ghcr.io/kreuzberg-dev/kreuzcrawl:0.3.0`. You can also paste the ready-made client config above.

07 · Alternatives to Kreuzcrawl

Alternatives to Kreuzcrawl

Maintained web scraping servers if Kreuzcrawl isn't the fit.

Pairs well with

Servers that cover what Kreuzcrawl doesn't - only shown when the pairing reason fits the companion.

More web scraping MCP servers · Web Fetch MCP · Fiverr MCP Server · Xcatcher - Recent X Posts · Tapsite · Agent402.Tools: pay-per-call web tools

More Rust MCP servers · Topos · Limpet · Sophon · Sys Knife · Leakferret · see all