Crawlberg MCP Server

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

People who work with crawling, elixir and ffi and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Rust.

VERIFIED ACTIVE

LAST COMMIT 2026-09-28 · ★ 179 · #50 OF 97 MAINTAINED WEB SCRAPING · VERIFIED 2026-09-30

MIT · Rust servers · how we verify → /methodology

01 · Install Crawlberg

Docker

docker run -i --rm ghcr.io/xberg-io/crawlberg:1.8.0

Claude Desktop - add to config

{
  "mcpServers": {
    "xberg-io-crawlberg": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/xberg-io/crawlberg:1.8.0"
      ]
    }
  }
}

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.xberg-io is GitHub-verified and matches the repo owner

03 · What Crawlberg can do

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

Latest releases

v1.8.0 · 2026-09-27

Includes twelve issues raised by an external evaluation, ten of them in the crawl path. Most were · defects a green e2e suite could not see: the fixtures covering the affected behaviours passed with · the bugs fully…

v1.7.2 · 2026-09-24

A wasm and kotlin_android correctness release. A wasm engine handle was unusable after one call, · and the kotlin_android e2e suite had never once completed a run. Both traced to the binding · generator, so the fixes…

v1.7.1 · 2026-09-16

A release-tooling fix. 1.7.0's Java artifact never reached Maven Central; this version carries the · fix and publishes it. No library code changed, so 1.7.0 and 1.7.1 are byte-identical apart from the · version string…

04 · Who maintains Crawlberg

Crawlberg is maintained by xberg-io. It's the only MCP server we track from this author; the repo dates to Mar 2026.

05 · Facts

repository: github.com/xberg-io/crawlberg
website: https://xberg.io/
category: web scraping - ranked #50 of 97 actively-maintained web scraping servers as of 2026-09-30.
release cadence: 10+ releases in the last 90 days (latest 2026-09-27)
registry: io.github.xberg-io/crawlberg (active, first published 2026-06-26 · 34 versions)
packages: oci:ghcr.io/xberg-io/crawlberg:1.8.0

06 · Crawlberg FAQ

What is Crawlberg?

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

Is Crawlberg still maintained?

Yes - as of 2026-09-30, its last commit was 2026-09-28 and it shipped 10+ releases in the last 90 days. We re-verify nightly.

How do I install Crawlberg?

Run `docker run -i --rm ghcr.io/xberg-io/crawlberg:1.8.0`. You can also paste the ready-made client config above.

07 · Alternatives to Crawlberg

Alternatives to Crawlberg

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

Pairs well with

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

More web scraping MCP servers · Xquik MCP Server · AI-First Scraper · Zenrows MCP · Web Researcher MCP · Librecrawl - Technical SEO Audit MCP Server

More Rust MCP servers · DeepSeek Visionary · Aginx Browser · Citadel · Zenith · Unterm · see all