- What it does
- Check an llms.txt file against the llmstxt.org proposal: H1 title, blockquote summary, H2 file lists of [name](url): notes items, the Optional section, every fault with its line, and a signed record.
- Who it is for
- Agents and their builders.
- Start in one step
- Ask your agent to call
llms_txt_checkat llpro.ai/mcp (free, no sign-up). This page explains the tool; it has no form to run it. - What to expect
- Testing: open to try. Free
New to this? Start here.
What it does
llms.txt Structure Check (llmstxt.org) is for agents and developers that publish or read llms.txt files so other agents can find a site's documentation, and need the structure checked the same way every time. Check an llms.txt file against the llmstxt.org proposal (v2, August 2026) before you publish it or rely on one. Send the file text (up to 20,000 characters). Get back whether it follows the proposal's structure: the H1 title first, the blockquote summary, the details part with no headings, H2 sections holding file lists, each item a markdown link [name](url) with optional ': notes', and the Optional section; every fault with its line number and what to change; warnings for things the proposal does not forbid but agents trip on (plain http links, relative links, empty sections). The title, section names and link counts are given back; link targets are not fetched. It is one of the developer department tools LLPRO builds for the work agents do across business software (GitHub, Vercel, Netlify, Cloudflare). Every answer carries the written rule it used, what it does not do, its sources with dates, and an Ed25519 signature you can check against the key below.
- Who it is for
- Agents and developers that publish or read llms.txt files so other agents can find a site's documentation, and need the structure checked the same way every time.
- Price
- Free, no sign-up: 120 calls an hour per address and 3,000 an hour across all callers. Paid calls are planned and not charging.
- Limits
- Up to 30,000 bytes per call; larger requests are refused, never cut. Unknown fields are refused with the list of accepted ones. Nothing you send is stored by the tool; no model and no network are used. Does not fetch the file or its links, so it cannot say a link works or points to markdown (the proposal asks that links lead to LLM-friendly content such as .md pages). Does not judge the writing (the proposal's guidance: concise, clear, no unexplained jargon). Does not read setext (underlined) headings as headings: write '# Title'. llms.txt is a community proposal, not an IETF or W3C standard, and agents differ in how strictly they read it. Up to 20,000 characters per call; each character outside US-ASCII counts as 6 bytes toward the 30,000-byte request limit. Not legal advice.
For developers: try it
POST https://llpro.ai/mcp
{"jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": {"name": "llms_txt_check", "arguments": {"llms_txt": "# FastHTML\n\n> FastHTML is a python library for creating server-rendered hypermedia applications.\n\nImportant notes:\n\n- It is *not* compatible with FastAPI syntax.\n\n## Docs\n\n- [FastHTML quick start](https://fastht.ml/docs/tutorials/quickstart_for_web_devs.html.md): A brief overview of many FastHTML features\n- [HTMX reference](https://github.com/bigskysoftware/htmx/blob/master/www/content/reference.md)\n\n## Optional\n\n- [Starlette docs](https://example.org/starlette-sml.md): A subset of the Starlette documentation\n"}}}For agents
Tool llms_txt_check on https://llpro.ai/mcp and in the tools list. Signed answers are checked with the public key below (signer llpro1:ij2ftarxpzgktirgoduazvcsva): an Ed25519 signature over the observation as canonical JSON (sorted keys, no spaces).
Public key (base64): z8tABfnpCVdnBpW1NsQp21wzVovzlwwFhg7dcVv1hLA=
For agents that search MCP registries for llms.txt, llmstxt.org, agent documentation tools (listed in MCP registries, served by the Campus gateway: MCP, agent-to-agent and REST). One fixed, written rule per call, a signed record, no account needed.
Next
- Connect your agent: Use this and the other LLPRO tools from your own agent.
- Get your agent: No agent yet? Get one that asks first.
- Hand the whole job to the Hub: Checking llms.txt is one step of making a site readable by agents. Tell the Hub the whole job; it routes you to the right signed tools (agent card check, robots.txt check, sitemap reader).
For agents: this page as Markdown · JSON · llms.txt · MCP endpoint llpro.ai/mcp · agent card