# ExtractMCP (pypi · mcpproducts-extract)

Turn any URL or HTML into clean markdown, tables, links or JSON for agents

- Trust score: 58/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-16

## Components

- pypi · `mcpproducts-extract`: 58/100 (this document), [markdown](https://verifymcp.io/servers/com-mcpproducts-extract/mcpproducts-extract.md), [page](https://verifymcp.io/servers/com-mcpproducts-extract/mcpproducts-extract)

## Channel facts

- Registry: `pypi`
- Package: `mcpproducts-extract`
- Version: `0.1.1`
- 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 2026-10-16.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 3 of 48 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 6/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 0 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 283 tokens (~47/item across 6 items; 6 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**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% 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 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (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 ExtractMCP MCP server?

ExtractMCP runs locally as a PyPI package, launched with uvx mcpproducts-extract. 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 com-mcpproducts-extract -- uvx mcpproducts-extract
```

### Cursor

```json
{
  "mcpServers": {
    "com-mcpproducts-extract": {
      "command": "uvx",
      "args": [
        "mcpproducts-extract"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-mcpproducts-extract": {
      "command": "uvx",
      "args": [
        "mcpproducts-extract"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add com-mcpproducts-extract -- uvx mcpproducts-extract
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-mcpproducts-extract": {
      "type": "local",
      "command": [
        "uvx",
        "mcpproducts-extract"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-mcpproducts-extract --command uvx --arg mcpproducts-extract
```

### Hermes

```yaml
mcp_servers:
  com-mcpproducts-extract:
    command: "uvx"
    args: ["mcpproducts-extract"]
```

### Netclaw

```json
{
  "McpServers": {
    "com-mcpproducts-extract": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "mcpproducts-extract"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-mcpproducts-extract -t stdio -c uvx -a mcpproducts-extract
```

### Other

```json
{
  "mcpServers": {
    "com-mcpproducts-extract": {
      "command": "uvx",
      "args": [
        "mcpproducts-extract"
      ]
    }
  }
}
```

## 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.

### 2026-10-16 (score 58, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-15 (score 43)

First indexed and scored.

## MCP tools (6)

### `extract_text` (~28 tokens)

Clean readable text from an HTML string (scripts/styles/nav stripped).

Input parameters:

- `html` (string, required)

Output parameters:

- `result` (string)

### `fetch_markdown` (~45 tokens)

URL -> clean readable markdown (trafilatura if available; stdlib fallback). Headings preserved when possible.

Input parameters:

- `links` (boolean)
- `url` (string, required)

Output parameters:

- `result` (string)

### `extract_tables` (~41 tokens)

Extract all HTML tables from a URL or raw HTML as JSON arrays of rows.

Input parameters:

- `min_rows` (integer)
- `url_or_html` (string, required)

Output parameters:

- `result` (string)

### `extract_links` (~55 tokens)

All links from a URL or HTML: [{text, href}] (relative hrefs resolved against base_url/page).

Input parameters:

- `base_url` (string)
- `limit` (integer)
- `url_or_html` (string, required)

Output parameters:

- `result` (string)

### `extract_json` (~44 tokens)

Fetch a JSON endpoint and return it (optionally select a dotted path like 'data.items.0.title').

Input parameters:

- `path` (string)
- `url` (string, required)

Output parameters:

- `result` (string)

### `cloud_extract` (~70 tokens)

PREMIUM (needs MPX_API_KEY): cloud extraction for JS-rendered pages (SPA/React)
and batch jobs — a real browser renders the page server-side, then returns clean data.

fmt: markdown | text | json | html.

Input parameters:

- `fmt` (string)
- `url` (string, required)

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-mcpproducts-extract/mcpproducts-extract#diagnostics

## Score history

- 2026-10-16: 58
- 2026-10-15: 43

## Common questions

### What is the ExtractMCP MCP server?

ExtractMCP is an MCP server listed in the public MCP registry as com.mcpproducts/extract. Turn any URL or HTML into clean markdown, tables, links or JSON for agents. This page covers its PyPI package (mcpproducts-extract).

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

ExtractMCP scores 58 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 16 October 2026. 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 ExtractMCP MCP server expose?

ExtractMCP exposes 6 tools: extract_text, fetch_markdown, extract_tables, extract_links, extract_json, cloud_extract. Their descriptions and schemas cost roughly 283 tokens of context every time the server is loaded.

### Is the ExtractMCP MCP server still maintained?

ExtractMCP is still listed as active in the MCP registry. We last reached this channel on 16 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- PyPI project: https://pypi.org/project/mcpproducts-extract/
- Socket report: https://socket.dev/pypi/package/mcpproducts-extract
- Website: https://gw.mcpproducts.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-mcpproducts-extract/mcpproducts-extract.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-mcpproducts-extract/mcpproducts-extract.json
- HTML version of this page: https://verifymcp.io/servers/com-mcpproducts-extract/mcpproducts-extract