# MTScraper (npm · mtscraper)

Free local crawler: any site, JavaScript pages and linked PDFs, into clean text.

- Trust score: 66/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `mtscraper`: 66/100 (this document), [markdown](https://verifymcp.io/servers/mazprotech-mtscraper/mtscraper.md), [page](https://verifymcp.io/servers/mazprotech-mtscraper/mtscraper)

## Channel facts

- Registry: `npm`
- Package: `mtscraper`
- Version: `2.1.1`
- 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 2026-11-21.

- **Supply Chain Security**: 81/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects pdfjs-dist 5.7.284, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - 106 of 391 dependencies flagged as unhealthy (3 deprecated).
- **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 (MIT).
  - Actively maintained (last published 5 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 76/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 360 tokens (~120/item across 3 items; 3 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 3 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.

**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 MTScraper MCP server?

MTScraper runs locally as an npm package, launched with npx -y mtscraper --mcp. 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 mazprotech-mtscraper -- npx -y mtscraper --mcp
```

### Cursor

```json
{
  "mcpServers": {
    "mazprotech-mtscraper": {
      "command": "npx",
      "args": [
        "-y",
        "mtscraper",
        "--mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "mazprotech-mtscraper": {
      "command": "npx",
      "args": [
        "-y",
        "mtscraper",
        "--mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add mazprotech-mtscraper -- npx -y mtscraper --mcp
```

### opencode

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

### Hermes

```yaml
mcp_servers:
  mazprotech-mtscraper:
    command: "npx"
    args: ["-y", "mtscraper", "--mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "mazprotech-mtscraper": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "mtscraper",
        "--mcp"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "mazprotech-mtscraper": {
      "command": "npx",
      "args": [
        "-y",
        "mtscraper",
        "--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.

### 2026-11-16 (score 66, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-15 (score 51)

First indexed and scored.

## MCP tools (3)

### `crawl` (~199 tokens)

Crawl a website into clean text

Crawls a site from the start URL, following internal links (same domain) and linked PDFs, and returns one record per page: url, title, view, type (html|pdf), text, tables. Obeys robots.txt. Results are also written to a JSONL file whose path is returned.

Input parameters:

- `click` (string): CSS selector of tabs/buttons to click on single-page apps, saving every view
- `follow` (string): Only follow links whose URL contains this text, e.g. /docs/
- `format` (string): text (default) or markdown, which keeps headings, lists, links and tables
- `js` (boolean): Render pages in headless Chromium for JavaScript sites (slower)
- `max_pages` (integer): Stop after this many pages (0 = no limit)
- `pdf` (boolean): Also download linked PDFs and extract their text and tables
- `url` (string, required): Start URL

### `read` (~87 tokens)

Read one web page

Fetches one page (or PDF) and returns its clean main content in the reply, as Markdown by default. Nothing is saved to a file. Obeys robots.txt.

Input parameters:

- `format` (string): markdown (default) or text
- `js` (boolean): Render the page in headless Chromium first, for JavaScript sites (slower)
- `url` (string, required): Page URL

### `map` (~74 tokens)

List a site's pages

Lists the pages of a site without downloading them: from its sitemap, or else from the links on the start page. Same site only; pages robots.txt blocks are left out.

Input parameters:

- `max_pages` (integer): List at most this many pages (0 = no limit)
- `url` (string, required): Start URL of the site

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/mazprotech-mtscraper/mtscraper#diagnostics

## Score history

- 2026-11-21: 66
- 2026-11-20: 66
- 2026-11-19: 66
- 2026-11-18: 66
- 2026-11-17: 66
- 2026-11-16: 66
- 2026-11-15: 51

## Common questions

### What is the MTScraper MCP server?

MTScraper is an MCP server listed in the public MCP registry as io.github.mazprotech/mtscraper. Free local crawler: any site, JavaScript pages and linked PDFs, into clean text. This page covers its npm package (mtscraper).

### Is the MTScraper MCP server safe to use?

MTScraper scores 66 out of 100 on VerifyMCP. We recorded 3 known advisories against it as of 21 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 MTScraper MCP server expose?

MTScraper exposes 3 tools: crawl, read, map. Their descriptions and schemas cost roughly 360 tokens of context every time the server is loaded.

### Is the MTScraper MCP server still maintained?

MTScraper is still listed as active in the MCP registry. We last reached this channel on 21 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 MTScraper MCP server under?

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

### What did VerifyMCP test on the MTScraper MCP server?

VerifyMCP ran 15 checks on MTScraper, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about MTScraper: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/mtscraper
- Socket report: https://socket.dev/npm/package/mtscraper
- Repository: https://github.com/mazprotech/mtscraper
- Changelog RSS feed: https://verifymcp.io/servers/mazprotech-mtscraper/mtscraper.xml
- Changelog JSON feed: https://verifymcp.io/servers/mazprotech-mtscraper/mtscraper/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/mazprotech-mtscraper/mtscraper.json
- HTML version of this page: https://verifymcp.io/servers/mazprotech-mtscraper/mtscraper
