# llms.ink (remote · llms.ink)

Any link as llms.txt; check llms.txt; see how AI crawlers read a page; draft AGENTS.md.

- Trust score: 68/100 (medium)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `llms.ink`: 68/100 (this document), [markdown](https://verifymcp.io/servers/ink-llms-llms-ink/llms.md), [page](https://verifymcp.io/servers/ink-llms-llms-ink/llms)

## Channel facts

- Endpoint: `https://llms.ink/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.7.0`

## 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 2026-11-21.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1631 tokens (~233/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 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 llms.ink MCP server?

llms.ink is a hosted endpoint at https://llms.ink/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 ink-llms-llms-ink 'https://llms.ink/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "ink-llms-llms-ink": {
      "url": "https://llms.ink/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ink-llms-llms-ink": {
      "type": "http",
      "url": "https://llms.ink/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.ink-llms-llms-ink]
url = "https://llms.ink/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ink-llms-llms-ink": {
      "type": "remote",
      "url": "https://llms.ink/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ink-llms-llms-ink --url 'https://llms.ink/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ink-llms-llms-ink:
    url: "https://llms.ink/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "ink-llms-llms-ink": {
      "Transport": "http",
      "Url": "https://llms.ink/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add ink-llms-llms-ink -t streamable-http -u 'https://llms.ink/mcp'
```

### Other

```json
{
  "mcpServers": {
    "ink-llms-llms-ink": {
      "type": "http",
      "url": "https://llms.ink/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.

### 2026-11-20 (score 68, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “llms_txt” rewrote its description, which is the text the model reads

### 2026-11-18 (score 67, 0)

- [functional regression] Schema quality: 206 → 230
- [functional] Server version: 0.6.0 → 0.7.0
- [cosmetic] “llms_full_txt” added an optional parameter “crawl”
- [cosmetic] “llms_txt” added an optional parameter “crawl”

### 2026-11-17 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 66, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “check_llms_txt” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 162 → 206
- [functional regression] Schema quality: 162 → 205
- [functional regression] Schema quality: 649 → 891
- [functional improvement] Stability: unverified → 0.03
- [functional] Server version: 0.5.0 → 0.6.0
- [functional] Server version: 0.4.0 → 0.5.0
- [functional] Server version: 0.2.0 → 0.4.0
- [functional] New tool “agent_view”
- [functional] New tool “generate_draft”
- [functional] New tool “create_clip_link”
- [cosmetic] “check_llms_txt” added an optional parameter “base”
- [cosmetic] “check_llms_txt” added an optional parameter “links”
- [cosmetic] “check_llms_txt” added an optional parameter “text”
- [cosmetic] “check_llms_txt” reworded the description of “url”
- [cosmetic] “check_llms_txt” made “url” optional
- [cosmetic] Tool “check_llms_txt” changed its title: Check a published llms.txt → Check an llms.txt

### 2026-11-13 (score 66)

First indexed and scored.

## MCP tools (7)

### `create_clip_link` (~188 tokens)

Open a transcript passage as a clip

Return a Gimmeclip selection link for 0.5–60 seconds of a public YouTube, Instagram, TikTok, X, Facebook, Bluesky, VK, LinkedIn or Weibo video. Read llms_full_txt first to choose source-video timestamps. The user opens the link to preview, adjust and create the clip. Does not render, download, or verify that the video is available. For a finished watch link use share_video on https://gimmeclip.com/mcp.

Input parameters:

- `end` (number, required): End in source-video seconds; 0.5–60 seconds after start.
- `start` (number, required): Start in source-video seconds.
- `url` (string, required): Any public http(s) link, e.g. "docs.stripe.com/payments", "github.com/honojs/hono", a PDF or a video URL. The scheme is optional.

### `llms_txt` (~206 tokens)

llms.txt for a link

Get an llms.txt index for any link: title, one-line summary, and sections of the most useful links with short descriptions. Returns the site’s own llms.txt when it has one, with hidden instructions removed. Cached 24h.

Input parameters:

- `crawl` (integer): A channel or profile only: how many of its newest items are opened and described (0–10). Defaults: YouTube 5, GitHub 5, Instagram 4, TikTok 4, X 5. Another depth is cached apart and, when built, coun…
- `fresh` (boolean): Ignore the 24h cache and rebuild. Default false.
- `url` (string, required): Any public http(s) link, e.g. "docs.stripe.com/payments", "github.com/honojs/hono", a PDF or a video URL. The scheme is optional.

### `llms_full_txt` (~224 tokens)

llms-full.txt for a link

Get llms-full.txt for any link: the llms.txt index followed by the full Markdown of up to 20 pages it links to (or the page/document itself; for a video, its description and timestamped transcript). Can be large — prefer llms_txt when you only need to find pages. Cached 24h.

Input parameters:

- `crawl` (integer): A channel or profile only: how many of its newest items are opened and described (0–10). Defaults: YouTube 5, GitHub 5, Instagram 4, TikTok 4, X 5. Another depth is cached apart and, when built, coun…
- `fresh` (boolean): Ignore the 24h cache and rebuild. Default false.
- `url` (string, required): Any public http(s) link, e.g. "docs.stripe.com/payments", "github.com/honojs/hono", a PDF or a video URL. The scheme is optional.

### `video_frame` (~149 tokens)

Frame of a video

Get one frame of a video (YouTube, Instagram, X, TikTok, a direct .mp4 link…) as a JPEG image, to see what is on screen at a given time. Pair with llms_full_txt: the transcript is timestamped.

Input parameters:

- `t` (string): Time in the video: seconds ("90", "90.5") or "1:30" / "1:02:03". Default "0".
- `url` (string, required): The video link, e.g. "youtube.com/watch?v=…" or "instagram.com/reel/…". The scheme is optional.
- `width` (integer): Maximum width in pixels. Default 1280.

### `check_llms_txt` (~252 tokens)

Check an llms.txt

Check an llms.txt against the format (H1 title, blockquote summary, H2 sections of `- [name](url): notes` links) and size. Pass `url` to check the file a site publishes, including whether its first 25 links answer; or pass `text` to check a file you have (a draft, a local copy), with `base` for where it lives and `links` to also test its links. Returns a short report with each issue and its line, and the sections with their link counts.

Input parameters:

- `base` (string): With text: the site or llms.txt link it belongs to, e.g. "example.com". Resolves relative links.
- `links` (boolean): With text: also check that its first 25 links answer (and llms-full.txt next to base). Default false.
- `text` (string): The llms.txt itself (up to 2 MB), instead of url.
- `url` (string): A site, a docs section, or the llms.txt itself, e.g. "llmstxt.org" or "docs.astro.build/llms.txt". Use url or text.

### `generate_draft` (~220 tokens)

Draft AGENTS.md, JSON-LD, alt text or answer-first headings

Draft fixes for a site or repo owner to review, each tied to its sources. kind `agents-md`: an AGENTS.md (setup, commands, layout, conventions) for a GitHub repo or docs site, every line citing its file and line. `jsonld`: WebSite/Organization/Product/SoftwareApplication JSON-LD built only from facts on the site. `alt-text`: alt text for images missing it, from image descriptions. `answers`: per H2 section, a question-shaped heading and an answer-first sentence drawn only from that section. Drafts never contain URLs, commands or numbers not in the sources. Cached 24h; counts as a new link.

Input parameters:

- `fresh` (boolean): Ignore the 24h cache and regenerate. Default false.
- `kind` (string, required): What to draft.
- `url` (string, required): Any public http(s) link, e.g. "docs.stripe.com/payments", "github.com/honojs/hono", a PDF or a video URL. The scheme is optional.

### `agent_view` (~175 tokens)

What AI agents see on a page

Report how AI crawlers and agents see a page: robots.txt per AI bot (search, user fetches, training) and Content-Signal, firewall blocks found by fetching with bot User-Agents, text present without JavaScript, what survives Markdown conversion, title/first paragraph/facts/noindex/canonical/sitemap, hidden instructions, and llms.txt, .md URLs, Accept: text/markdown, Link headers, ard.json. Each check is pass/warn/fail/info with a fix; robots.txt and header fixes include the changed file. Use it to tell a site owner why assistants can’t read or cite a page and what to change.

Input parameters:

- `url` (string, required): A site or any page on it, e.g. "example.com" or "docs.example.com/guide". The scheme is optional.

## Diagnostics

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

## Score history

- 2026-11-21: 68
- 2026-11-20: 68
- 2026-11-19: 67
- 2026-11-18: 67
- 2026-11-17: 67
- 2026-11-16: 66
- 2026-11-15: 66
- 2026-11-14: 66
- 2026-11-13: 66

## Common questions

### What is the llms.ink MCP server?

llms.ink is an MCP server listed in the public MCP registry as ink.llms/llms-ink. Any link as llms.txt; check llms.txt; see how AI crawlers read a page; draft AGENTS.md. This page covers its hosted endpoint (https://llms.ink/mcp).

### Is the llms.ink MCP server safe to use?

llms.ink scores 68 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 llms.ink MCP server expose?

llms.ink exposes 7 tools: create_clip_link, llms_txt, llms_full_txt, video_frame, check_llms_txt, and 2 more. Their descriptions and schemas cost roughly 1,414 tokens of context every time the server is loaded.

### Does the llms.ink MCP server require authentication?

No. We connected to llms.ink without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the llms.ink MCP server still maintained?

llms.ink 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 did VerifyMCP test on the llms.ink MCP server?

VerifyMCP ran 12 checks on llms.ink, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about llms.ink: HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://llms.ink/mcp
- Website: https://llms.ink/docs/
- Changelog RSS feed: https://verifymcp.io/servers/ink-llms-llms-ink/llms.xml
- Changelog JSON feed: https://verifymcp.io/servers/ink-llms-llms-ink/llms/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/ink-llms-llms-ink/llms.json
- HTML version of this page: https://verifymcp.io/servers/ink-llms-llms-ink/llms
