CRW Web Scraper MCP Server

Turn URLs into clean markdown or structured JSON with one engine for search, scrape, map, crawl, and extract.

People who work with crawler, data extraction and docker and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Rust.

VERIFIED ACTIVE

LAST COMMIT 2026-09-30 · ★ 1,088 · #30 OF 97 MAINTAINED WEB SCRAPING · VERIFIED 2026-09-30

AGPL-3.0 · Rust servers · how we verify → /methodology

01 · Install CRW Web Scraper

before you install - you'll need

CRW_API_KEY

Environment variables documented in the project's README - it lists which are required and which have defaults.

Docker

docker run -i --rm ghcr.io/fastcrw/crw:latest

Claude Desktop - add to config

{
  "mcpServers": {
    "fastcrw-crw": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/fastcrw/crw:latest"
      ]
    }
  }
}

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 AGPL-3.0 - declared in the repository

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

03 · What CRW Web Scraper can do

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

Latest releases

v0.37.0 · 2026-09-29

0.37.0 (2026-09-29) · advertise maxAge on crw_scrape so callers can tune the fetch cache · reach the solver tier on hosts that block datacenter addresses · expose and clear the per-host renderer preference learner…

v0.36.0 · 2026-09-19

0.36.0 (2026-09-19) · cache the fetch so a repeat scrape skips the network · do not fail a job because robots.txt could not be read · keep the last robots rule of a file that lands on the size cap · accumulate usage…

v0.35.1 · 2026-09-10

0.35.1 (2026-09-10) · cross-compile BoringSSL for the arm64 image leg

04 · Who maintains CRW Web Scraper

CRW Web Scraper is maintained by fastcrw. It's the only MCP server we track from this author; the repo dates to Mar 2026.

05 · Facts

repository: github.com/fastcrw/crw
website: https://fastcrw.com/
category: web scraping - ranked #30 of 97 actively-maintained web scraping servers as of 2026-09-30.
release cadence: 10+ releases in the last 90 days (latest 2026-09-29)
registry: io.github.fastcrw/crw (active, first published 2026-09-30)
packages: oci:ghcr.io/fastcrw/crw:latest

06 · CRW Web Scraper FAQ

What is CRW Web Scraper?

Turn URLs into clean markdown or structured JSON with one engine for search, scrape, map, crawl, and extract.

Is CRW Web Scraper still maintained?

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

How do I install CRW Web Scraper?

Run `docker run -i --rm ghcr.io/fastcrw/crw:latest`. The README documents one environment variable (CRW_API_KEY) to set first. You can also paste the ready-made client config above.

07 · Alternatives to CRW Web Scraper

Alternatives to CRW Web Scraper

Maintained web scraping servers if CRW Web Scraper isn't the fit.

Pairs well with

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

More web scraping MCP servers · Fouradata MCP Server · Glim Sh · Gmapsscraper MCP Server · GoAnyAPI MCP

More Rust MCP servers · Kin · Glass · Llmtrim · Flash · mwe-MCP - Memory Wiki Engine · see all