# Hydrafetch (remote · api.hydrafetch.com)

Turn any URL into clean Markdown and structured data. Scrape, crawl, search and extract.

- Trust score: 95/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `api.hydrafetch.com`: 95/100 (this document), [markdown](https://verifymcp.io/servers/com-hydrafetch-web/api.md), [page](https://verifymcp.io/servers/com-hydrafetch-web/api)

## Channel facts

- Endpoint: `https://api.hydrafetch.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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 2026-09-20.

- **Endpoint Security**: 97/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
  - The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 79/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1077 tokens (~82/item across 13 items; 13 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **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 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 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 Hydrafetch MCP server?

Hydrafetch is a hosted endpoint at https://api.hydrafetch.com/mcp, so there is nothing to install locally. 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 --transport http com-hydrafetch-web 'https://api.hydrafetch.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-hydrafetch-web": {
      "url": "https://api.hydrafetch.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-hydrafetch-web": {
      "type": "http",
      "url": "https://api.hydrafetch.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-hydrafetch-web]
url = "https://api.hydrafetch.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-hydrafetch-web": {
      "type": "remote",
      "url": "https://api.hydrafetch.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-hydrafetch-web --url 'https://api.hydrafetch.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-hydrafetch-web:
    url: "https://api.hydrafetch.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-hydrafetch-web": {
      "Transport": "http",
      "Url": "https://api.hydrafetch.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-hydrafetch-web -t streamable-http -u 'https://api.hydrafetch.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-hydrafetch-web": {
      "type": "http",
      "url": "https://api.hydrafetch.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-09-19 (score 95, 0)

- [security] Stability: 0.97 → pass

### 2026-09-18 (score 95, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-16 (score 94, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 93, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-12 (score 92, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-10 (score 91, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-08 (score 90, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-06 (score 89, +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.

## MCP tools (13)

### `scrape` (~103 tokens)

Scrape

Turn a URL into clean, LLM-ready markdown and structured data.

Input parameters:

- `formats` (array): Which outputs to return. Defaults to markdown.
- `preferStructure` (boolean): Keep headings, lists and tables as markdown. Default false optimises for raw content and can return unstructured text on marketing and listing pages. Turn on when the document structure matters, or r…
- `url` (string, required): The URL to scrape.

### `map` (~45 tokens)

Map

Enumerate a site's URLs from its sitemap and links, without scraping them.

Input parameters:

- `limit` (integer): Max URLs to return.
- `url` (string, required): The seed URL to map.

### `crawl` (~78 tokens)

Crawl

Discover and scrape a whole site as one job. Returns a crawl id straight away; read it with crawl_status. Use this instead of calling scrape in a loop.

Input parameters:

- `limit` (integer): Maximum pages to scrape.
- `maxDepth` (integer): How far from the seed to follow.
- `url` (string, required): The site to start from.

### `crawl_status` (~41 tokens)

Crawl status

Read a crawl started with crawl: how far it has got, and the pages it has scraped.

Input parameters:

- `crawlId` (string, required): The id returned by crawl.

### `batch` (~44 tokens)

Batch

Scrape a list of URLs you already have as one job. Returns a batch id straight away; read it with batch_status.

Input parameters:

- `urls` (array, required): The URLs to scrape.

### `batch_status` (~40 tokens)

Batch status

Read a batch started with batch: how far it has got, and the results so far.

Input parameters:

- `batchId` (string, required): The id returned by batch.

### `search` (~105 tokens)

Search

Search the web and return ranked results: title, url and snippet. Set scrapeResults to also fetch each result as markdown, at 1 extra credit per page.

Input parameters:

- `limit` (integer): Max results (default 5).
- `preferStructure` (boolean): Keep headings, lists and tables in each scraped result.
- `query` (string, required): The search query.
- `scrapeResults` (boolean): Also scrape each result to markdown, 1 extra credit per page (default false).

### `brand` (~68 tokens)

Brand

A company's brand from its domain: logos for light and dark backgrounds, its real colours, name, description and socials. Answers 'what is this company' far better than a raw page dump.

Input parameters:

- `domain` (string, required): The company domain, e.g. stripe.com. A full URL works too.

### `logo` (~115 tokens)

Logo

A company's logo as a directly embeddable image URL, chosen for the background you name. Use this rather than brand when the mark is all you need — it costs a fifth as much and returns one asset instead of the whole record.

Input parameters:

- `domain` (string, required): The company domain, e.g. stripe.com. A full URL works too.
- `theme` (string): The background the logo will sit on. Defaults to light.
- `type` (string): The square mark, or the full logotype. Defaults to icon.

### `extract` (~84 tokens)

Extract

Pull typed structured data from one or more URLs by JSON schema or prompt.

Input parameters:

- `preferStructure` (boolean): Keep headings, lists and tables in the text handed to the model.
- `prompt` (string): Natural-language description of what to pull.
- `schema` (object): A JSON schema the result must conform to.
- `urls` (array, required): The URLs to extract from.

### `styleguide` (~75 tokens)

Styleguide

A site's design system read from computed styles in a real browser: colours by role with contrast ratios, the type scale, corner radius and button styling. Values defined through CSS variables come back resolved to the hex actually painted.

Input parameters:

- `domain` (string, required): The domain to read, e.g. stripe.com. A full URL works too.

### `screenshot` (~228 tokens)

Screenshot

Render a page in a real browser and capture a PNG, returning its public URL. Use when the question is what the page looks like rather than what it says.

Input parameters:

- `fullPage` (boolean): Capture the whole scrollable page rather than the viewport.
- `maxAge` (integer): Reuse a stored screenshot younger than this many milliseconds. Defaults to 7 days, so a repeat returns the stored PNG without re-rendering and without applying waitFor. Pass 0 to force a fresh captur…
- `timeout` (integer): Overall time budget for the capture, in milliseconds.
- `url` (string, required): The URL to capture.
- `viewport` (string): Screen size to render at. Defaults to desktop (1920x1080). Ignored when width or height are given.
- `viewportHeight` (integer): Exact viewport height in pixels. Overrides viewport. With fullPage the capture still extends to the full page height.
- `viewportWidth` (integer): Exact viewport width in pixels. Overrides viewport.
- `waitFor` (integer): Extra milliseconds to let the page settle before capture.

### `images` (~51 tokens)

Images

Harvest a page's images with their metadata, without rendering it. Cheaper than a screenshot and returns the source images rather than a picture of the page.

Input parameters:

- `url` (string, required): The page to harvest images from.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-hydrafetch-web/api#diagnostics

## Score history

- 2026-09-20: 95
- 2026-09-19: 95
- 2026-09-18: 95
- 2026-09-17: 94
- 2026-09-16: 94
- 2026-09-15: 93
- 2026-09-14: 93
- 2026-09-13: 92
- 2026-09-12: 92
- 2026-09-11: 91
- 2026-09-10: 91
- 2026-09-09: 90
- 2026-09-08: 90
- 2026-09-07: 89
- 2026-09-06: 89
- 2026-09-05: 88
- 2026-09-04: 88
- 2026-09-03: 88
- 2026-09-02: 87
- 2026-09-01: 87
- 2026-08-31: 86
- 2026-08-30: 86
- 2026-08-29: 85
- 2026-08-28: 85
- 2026-08-27: 84
- 2026-08-26: 84
- 2026-08-25: 82
- 2026-08-24: 82
- 2026-08-23: 81
- 2026-08-22: 81

## Common questions

### What is the Hydrafetch MCP server?

Hydrafetch is an MCP server listed in the public MCP registry as com.hydrafetch/web. Turn any URL into clean Markdown and structured data. Scrape, crawl, search and extract. This page covers its hosted endpoint (https://api.hydrafetch.com/mcp).

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

Hydrafetch scores 95 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 Hydrafetch MCP server expose?

Hydrafetch exposes 13 tools: scrape, map, crawl, crawl_status, batch, and 8 more. Their descriptions and schemas cost roughly 1,077 tokens of context every time the server is loaded.

### Does the Hydrafetch MCP server require authentication?

Yes. Hydrafetch asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Hydrafetch MCP server still maintained?

Hydrafetch is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.hydrafetch.com/mcp
- Website: https://hydrafetch.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-hydrafetch-web/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-hydrafetch-web/api.json
- HTML version of this page: https://verifymcp.io/servers/com-hydrafetch-web/api