# CRW Web Scraper (oci · ghcr.io/fastcrw/crw)

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

- Trust score: 47/100 (low)
- Change this week: +8
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- oci · `ghcr.io/fastcrw/crw`: 47/100 (this document), [markdown](https://verifymcp.io/servers/fastcrw-crw/ghcr-io-fastcrw-crw.md), [page](https://verifymcp.io/servers/fastcrw-crw/ghcr-io-fastcrw-crw)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/fastcrw/crw`
- Version: `latest`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-17.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (AGPL-3.0).
  - Actively maintained (last published 16 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 73/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1138 tokens (~142/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 57/100
  - Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 95% of tool parameters carry a description.
  - Structured output schemas are declared (38% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the CRW Web Scraper MCP server?

CRW Web Scraper runs locally as a container image, launched with docker run --rm -i ghcr.io/fastcrw/crw:latest. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add fastcrw-crw -- docker run --rm -i ghcr.io/fastcrw/crw:latest
```

### Cursor

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

### VS Code

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

### Codex

```bash
codex mcp add fastcrw-crw -- docker run --rm -i ghcr.io/fastcrw/crw:latest
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "fastcrw-crw": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/fastcrw/crw:latest"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  fastcrw-crw:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/fastcrw/crw:latest"]
```

### Netclaw

```json
{
  "McpServers": {
    "fastcrw-crw": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/fastcrw/crw:latest"
      ]
    }
  }
}
```

### Other

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

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-17 (score 47, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 46, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 45, +6)

- [functional improvement] Stability: unverified → 0.43

### 2026-09-30 (score 39)

First indexed and scored.

## MCP tools (8)

### `crw_scrape` (~201 tokens)

Scrape URL

Scrape one URL to markdown, HTML, or links.

Input parameters:

- `excludeTags` (array): CSS selectors to exclude
- `formats` (array): Output formats (default ["markdown"])
- `includeTags` (array): CSS selectors to include
- `maxLength` (integer): Max chars per content field; 0 = unbounded (default ~15000)
- `onlyMainContent` (boolean): Strip nav/footer; main content only (default true)
- `renderJs` (boolean): Force JS render (true), HTTP-only (false), omit = auto
- `renderer` (string): Pin renderer; browser tiers imply renderJs:true (default auto). 'camoufox' needs the opt-in tier configured. 'impersonated-http' is JS-less Chrome-TLS impersonation, never renderJs.
- `url` (string, required): URL to scrape
- `waitFor` (integer): Ms to wait after JS render for late content

### `crw_crawl` (~219 tokens)

Crawl site

Start an async site crawl; returns a job id to poll with crw_check_crawl_status.

Input parameters:

- `jsonSchema` (object): Optional. A JSON Schema (draft 2020-12) describing fields to extract from each page via an LLM, e.g. {"type":"object","properties":{"title":{"type":"string"}}}. Free-form object. Omit to crawl withou…
- `maxDepth` (integer): Max crawl depth (default 2)
- `maxPages` (integer): Max pages to crawl (default 10)
- `renderJs` (boolean): Force JS render (true), HTTP-only (false), omit = auto
- `renderer` (string): Pin renderer; browser tiers imply renderJs:true (default auto). 'camoufox' needs the opt-in tier configured. 'impersonated-http' is JS-less Chrome-TLS impersonation, never renderJs.
- `url` (string, required): Starting URL
- `waitFor` (integer): Ms to wait after JS render per page

### `crw_check_crawl_status` (~62 tokens)

Check crawl status

Poll an async crawl job and retrieve its pages.

Input parameters:

- `id` (string, required): Crawl job id from crw_crawl
- `maxLength` (integer): Max chars per page content field; 0 = unbounded (default ~15000)

### `crw_map` (~137 tokens)

Map site URLs

Discover URLs on a site via sitemap and/or a short crawl. Returns a URL list only, no page content.

Input parameters:

- `crawlFallback` (boolean): Supplement sitemap with a short BFS crawl (default true; false = sitemap-only)
- `limit` (integer): Max URLs to discover AND return; 0 = unbounded (default 100). Raise it (e.g. 50000) to pull deep/large sitemaps.
- `maxDepth` (integer): Max discovery depth (default 2)
- `url` (string, required): URL to map
- `useSitemap` (boolean): Use sitemap.xml (default true)

### `crw_extract` (~158 tokens)

Extract structured data

Extract structured JSON from URLs via a prompt and/or JSON schema. Async job — poll crw_check_extract_status with the returned id. Needs an LLM.

Input parameters:

- `basis` (boolean): Return per-field evidence: each top-level scalar property comes back with a source url, verbatim excerpt and honest status (supported/unverified/unsupported/notFound). Requires schema.
- `llmApiKey` (string): BYOK LLM API key
- `llmModel` (string)
- `llmProvider` (string)
- `prompt` (string): Free-text extraction objective (required unless schema is given)
- `schema` (object): JSON Schema constraining the extracted output
- `urls` (array, required): URLs to extract from

Output parameters:

- `id` (string)
- `status` (string)
- `success` (boolean)
- `urls` (integer)

### `crw_check_extract_status` (~44 tokens)

Check extract job status

Poll an extract job; returns status and, when complete, a per-URL results array.

Input parameters:

- `id` (string, required): Extract job id from crw_extract

Output parameters:

- `creditsUsed` (integer)
- `error` (string)
- `expiresAt` (string)
- `id` (string)
- `results` (array)
- `status` (string)
- `success` (boolean)
- `tokensUsed` (integer)

### `crw_cancel_extract` (~46 tokens)

Cancel extract job

Request cancellation of an extract job. Returns the canonical status; cancelling remains non-terminal until the claimed URL settles.

Input parameters:

- `id` (string, required): Extract job id from crw_extract

Output parameters:

- `creditsUsed` (integer)
- `error` (string)
- `expiresAt` (string)
- `id` (string)
- `results` (array)
- `status` (string)
- `success` (boolean)
- `tokensUsed` (integer)

### `crw_parse_file` (~176 tokens)

Parse PDF

Parse a local PDF (base64 in contentBase64) to markdown. No OCR: scanned PDFs return empty markdown with a warning.

Input parameters:

- `contentBase64` (string, required): Base64-encoded PDF bytes
- `filename` (string): Original filename (optional)
- `formats` (array): Output formats (default ["markdown"]); json/summary need a server LLM
- `jsonSchema` (object): Optional. A JSON Schema (draft 2020-12) describing fields to extract when formats includes "json", e.g. {"type":"object","properties":{"title":{"type":"string"}}}. Free-form object.
- `maxLength` (integer): Max chars per content field; 0 = unbounded (default ~15000)
- `parsers` (array): Parsers to apply (default ["pdf"])

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/fastcrw-crw/ghcr-io-fastcrw-crw#diagnostics

## Score history

- 2026-10-17: 47
- 2026-10-16: 46
- 2026-10-15: 46
- 2026-10-14: 46
- 2026-10-13: 45
- 2026-10-12: 39
- 2026-10-10: 39
- 2026-10-06: 39
- 2026-10-04: 39
- 2026-10-03: 39
- 2026-10-02: 39
- 2026-10-01: 39
- 2026-09-30: 39

## Common questions

### What is the CRW Web Scraper MCP server?

CRW Web Scraper is an MCP server listed in the public MCP registry as io.github.fastcrw/crw. Open-source web scraper for AI agents with scrape, crawl, and map tools. This page covers its container image (ghcr.io/fastcrw/crw).

### Is the CRW Web Scraper MCP server safe to use?

CRW Web Scraper scores 47 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the CRW Web Scraper MCP server expose?

CRW Web Scraper exposes 8 tools: crw_scrape, crw_crawl, crw_check_crawl_status, crw_map, crw_extract, and 3 more. Their descriptions and schemas cost roughly 1,043 tokens of context every time the server is loaded.

### Is the CRW Web Scraper MCP server still maintained?

CRW Web Scraper is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the CRW Web Scraper MCP server under?

CRW Web Scraper declares the AGPL-3.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- GitHub Container Registry: https://ghcr.io/fastcrw/crw
- Repository: https://github.com/fastcrw/crw
- Website: https://fastcrw.com/
- Changelog RSS feed: https://verifymcp.io/servers/fastcrw-crw/ghcr-io-fastcrw-crw.xml
- Changelog JSON feed: https://verifymcp.io/servers/fastcrw-crw/ghcr-io-fastcrw-crw.json
- HTML version of this page: https://verifymcp.io/servers/fastcrw-crw/ghcr-io-fastcrw-crw