# Webcrawl Anything (npm · @webcrawl/mcp)

Scrape, map, crawl, search and monitor the web. Runs locally with no API key, cites every source.

- Trust score: 68/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `webcrawl.app`: 38/100, [markdown](https://verifymcp.io/servers/brainfish-ai-webcrawl/webcrawl.md), [page](https://verifymcp.io/servers/brainfish-ai-webcrawl/webcrawl)
- npm · `@webcrawl/mcp`: 68/100 (this document), [markdown](https://verifymcp.io/servers/brainfish-ai-webcrawl/webcrawl-mcp.md), [page](https://verifymcp.io/servers/brainfish-ai-webcrawl/webcrawl-mcp)

## Channel facts

- Registry: `npm`
- Package: `@webcrawl/mcp`
- Version: `1.4.2`
- 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 2026-11-05.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 93 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1215 tokens (~121/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 90/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 69% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Webcrawl Anything MCP server?

Webcrawl Anything runs locally as an npm package, launched with npx -y @webcrawl/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add brainfish-ai-webcrawl -- npx -y @webcrawl/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "brainfish-ai-webcrawl": {
      "command": "npx",
      "args": [
        "-y",
        "@webcrawl/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "brainfish-ai-webcrawl": {
      "command": "npx",
      "args": [
        "-y",
        "@webcrawl/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add brainfish-ai-webcrawl -- npx -y @webcrawl/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "brainfish-ai-webcrawl": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@webcrawl/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add brainfish-ai-webcrawl --command npx --arg -y --arg @webcrawl/mcp
```

### Hermes

```yaml
mcp_servers:
  brainfish-ai-webcrawl:
    command: "npx"
    args: ["-y", "@webcrawl/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "brainfish-ai-webcrawl": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@webcrawl/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add brainfish-ai-webcrawl -t stdio -c npx -a -y @webcrawl/mcp
```

### Other

```json
{
  "mcpServers": {
    "brainfish-ai-webcrawl": {
      "command": "npx",
      "args": [
        "-y",
        "@webcrawl/mcp"
      ]
    }
  }
}
```

## 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.

### 2026-11-05 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-04 (score 67, +11)

- [security improvement] Known CVEs: unverified → pass
- [functional improvement] Stability: unverified → 0.03
- [functional improvement] Dependency health: unverified → 0.86
- [functional] Package version: 1.4.1 → 1.4.2

### 2026-11-03 (score 56)

First indexed and scored.

## MCP tools (10)

### `web_search` (~207 tokens)

Web search

Search the web. Use `category` for structured results (flights, hotels, real-estate, shopping with prices, news, local business, security: CVE records with CVSS, affected and fixed versions). Results are localised to the user unless a place is given.

Input parameters:

- `category` (string): e.g. general, news, shopping, flights, hotels, real-estate, business, security, academic, tech. See search_categories.
- `city` (string)
- `country` (string): ISO country code, e.g. AU
- `include_content` (boolean): Also fetch page markdown for each result (slower, more credits)
- `limit` (integer): Max results, default 5
- `query` (string, required): What to search for
- `sites` (array): Only these domains, e.g. ["booking.com"]
- `subcategory` (string): e.g. buy or rent for real-estate, cve for security

### `web_read` (~37 tokens)

Read a page

Fetch one URL and return its main content as markdown.

Input parameters:

- `no_cache` (boolean): Skip cached copy
- `url` (string, required)

### `web_parse` (~134 tokens)

Read a file

Read a PDF, Word/Excel/PowerPoint file, image, or audio/video file at a URL and return Markdown. Scanned PDF pages are OCR'd; audio/video is transcribed with timestamps. Pages it could not read are listed, never guessed.

Input parameters:

- `background` (boolean): Run as a background job for long files; returns a run id
- `language` (string): Spoken language hint, e.g. en
- `ocr` (string): auto (default) OCRs only scanned pages
- `pages` (array): 1-indexed PDF pages to read
- `url` (string, required)

### `web_parse_status` (~31 tokens)

Check a file read

Check a background web_parse run and return its Markdown when it has finished.

Input parameters:

- `id` (string, required)

### `web_map` (~57 tokens)

Map a site

List the URLs on a website (sitemap, robots and links). Use before scraping to pick the right pages.

Input parameters:

- `limit` (integer)
- `search` (string): Only URLs matching this text
- `url` (string, required)

### `web_crawl` (~47 tokens)

Crawl a site

Read several pages starting from a URL and return each as markdown. Capped at 25 pages.

Input parameters:

- `max_pages` (integer): Default 5
- `url` (string, required)

### `web_extract` (~56 tokens)

Extract structured data

Pull structured JSON from one URL. Describe what you want with `prompt`, or pass a JSON `schema`.

Input parameters:

- `prompt` (string)
- `schema` (object): JSON Schema for the output
- `url` (string, required)

### `web_rerank` (~48 tokens)

Rerank documents

Order your own documents by relevance to a query. Returns the best matches first.

Input parameters:

- `documents` (array, required)
- `query` (string, required)
- `top_k` (integer)

### `web_monitor` (~311 tokens)

Monitor web pages or sites

Watch a single page, a list of URLs, or a whole website section on a schedule. Supports natural-language `watch_for` focus, explicit `condition` rules (e.g. `price < 50`, `content contains "In Stock"`, `added_urls_count > 0`), and email or webhook notifications.

Input parameters:

- `action` (string): Action to perform (defaults to 'create' when url/urls given, else 'list')
- `condition` (string): Optional trigger rule expression, e.g. 'price < 50', 'content contains "In Stock"', 'added_urls_count > 0'
- `id` (string): Monitor ID (required for get, check, pause, resume, delete)
- `interval_minutes` (integer): Check interval in minutes (default 60)
- `max_pages` (integer): Max pages to sample when mode is 'site' (default 5)
- `mode` (string): Watch scope: page (default), urls, or site
- `name` (string): Optional friendly watch name
- `notify_email` (string): Email address to notify when triggered, or 'true' to use the account email
- `url` (string): Page or site URL to watch
- `urls` (array): Multiple URLs to watch when mode is 'urls'
- `watch_for` (string): What to watch for, e.g. 'Pricing tiers and discounts'
- `webhook_url` (string): HTTPS webhook URL to POST when triggered

### `search_categories` (~21 tokens)

Search categories

List the search categories, subcategories and filters web_search supports.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/brainfish-ai-webcrawl/webcrawl-mcp#diagnostics

## Score history

- 2026-11-05: 68
- 2026-11-04: 67
- 2026-11-03: 56

## Common questions

### What is the Webcrawl Anything MCP server?

Webcrawl Anything is an MCP server listed in the public MCP registry as io.github.brainfish-ai/webcrawl. Scrape, map, crawl, search and monitor the web. Runs locally with no API key, cites every source. This page covers its npm package (@webcrawl/mcp).

### Is the Webcrawl Anything MCP server safe to use?

Webcrawl Anything scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. 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 Webcrawl Anything MCP server expose?

Webcrawl Anything exposes 10 tools: web_search, web_read, web_parse, web_parse_status, web_map, and 5 more. Their descriptions and schemas cost roughly 949 tokens of context every time the server is loaded.

### Is the Webcrawl Anything MCP server still maintained?

Webcrawl Anything is still listed as active in the MCP registry. We last reached this channel on 5 November 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 Webcrawl Anything MCP server under?

Webcrawl Anything declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@webcrawl/mcp
- Socket report: https://socket.dev/npm/package/@webcrawl/mcp
- Repository: https://github.com/brainfish-ai/webcrawl-anything
- Changelog RSS feed: https://verifymcp.io/servers/brainfish-ai-webcrawl/webcrawl-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/brainfish-ai-webcrawl/webcrawl-mcp.json
- HTML version of this page: https://verifymcp.io/servers/brainfish-ai-webcrawl/webcrawl-mcp