llms.ink
Turn any website, GitHub repo, PDF or video link into llms.txt or llms-full.txt
Answered our latest tool-list check 9 hours ago with 7 tools. It will be marked verified after 3 successful checks in 7 days.
- Pricing
- Free
- Platforms
- Web, API, CLI
- Runs
- Remotely
- Version
- 0.6.0
- Listing updated
- 3 days ago
About llms.ink
llms.ink is a free MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.
llms.ink takes a public link and returns a Markdown file an AI model can read: a short llms.txt index of links, or an llms-full.txt with up to 20 pages inlined. If the site already publishes its own file, that is returned; otherwise one is generated. Results say what the link was (site, section, page, repo, document or video), whether the file is native or generated, the approximate token count, and which model wrote the descriptions.
The same service is available as a URL prefix, a JSON API with an OpenAPI 3.1 spec, a CLI (npx @lukax/llms-ink), a GitHub Action and this remote MCP server. Video links also return duration, thumbnail, transcript segments and download formats, with frame and media endpoints for further detail.
No API key is needed. New links are limited to 60 a day per IP, cached links are free, and results are cached for 24 hours per link and mode. A site can serve its own /llms.txt from llms.ink by proxying with native=0 and format=text.
Install
Run in a terminal
claude mcp add --transport http llms-ink https://llms.ink/mcpAdd to Settings → Connectors → Add custom connector
https://llms.ink/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"llms-ink": {
"url": "https://llms.ink/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"llms-ink": {
"type": "http",
"url": "https://llms.ink/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"llms-ink": {
"serverUrl": "https://llms.ink/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"llms-ink": {
"type": "http",
"url": "https://llms.ink/mcp"
}
}
}Tools this server provides (7)
Read directly from the server.
- create_clip_link
- 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
- llms_txt
- 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. Cached 24h.
- llms_full_txt
- 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.
- video_frame
- 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.
- check_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,
- generate_draft
- 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 H
- agent_view
- 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 che
What it does
- Link to llms.txt
- Builds an llms.txt index for a site, section, page or repo.
- Full-text mode
- mode=full inlines up to 20 pages into llms-full.txt.
- Video support
- Video results include duration, transcript segments and mp4 or m4a downloads.
- Native file detection
- Returns a site's own llms.txt when published, unless native=0.
- Self-serving proxy
- A site can serve its /llms.txt from llms.ink for caching.
- Several interfaces
- URL prefix, JSON API, CLI, GitHub Action and MCP.
Good for
- Give a model a clean index of a documentation site
- Feed a repository summary to a coding agent
- Get a transcript of a video as context
- Serve an llms.txt for a site without writing one
- Check whether a site already publishes llms.txt
Pricing
Free
No key needed; 60 new links a day per IP
Prices change. Check llms.ink before you buy.
llms.ink FAQ
Do I need an API key?
No. The docs say no key is required and cross-origin requests are supported.
What are the limits?
60 new links a day per IP. Cached links are free and results are cached for 24 hours.
How do I force a rebuild?
Pass fresh=1, which skips the cache and counts against the daily quota.
Is there a spec?
Yes, an OpenAPI 3.1 spec at /openapi.json.
Is llms.ink free?
Yes. llms.ink is free to use.
How do I add llms.ink to Claude Code?
Run this command in your terminal: claude mcp add --transport http llms-ink https://llms.ink/mcp
What are the best alternatives to llms.ink?
The closest alternatives to llms.ink are Scrapling MCP Server, Firecrawl MCP Server, Claude Code Ultimate Guide, SearXNG Search and NeuralVerge.
Alternatives to llms.ink

Scrapling MCP Server
MCP serverMCP server for AI clients to scrape sites with HTTP and stealth browser sessions
Runs locally- 17 tools
- Open source
- 104K GitHub stars
- Web search and scraping

Firecrawl MCP Server
MCP serverMCP server that lets AI agents search, scrape and interact with web pages
- 3 tools
- Remote
- Freemium
- 7.8K GitHub stars
- Web search and scraping

Claude Code Ultimate Guide
MCP serverMCP server for searching the Claude Code Ultimate Guide from any MCP client
Runs locally- Open source
- 6.5K GitHub stars
- AI models and LLM tooling

SearXNG Search
MCP serverMCP server for web search and page reading through a SearXNG instance
Runs locally- 3 tools
- Open source
- 1.4K GitHub stars
- Web search and scraping

NeuralVerge
MCP serverStructured, source-tagged business and people data from 300+ sources for agents
- 200 tools
- Remote
- Free trial
- 1 GitHub star
- Web search and scraping

AI-Powered directory
MCP serverSearch AI tools, agents and MCP servers and get install configs from inside your AI assistant.
- 4 tools
- Remote
- Free
- Developer tools