check_websiteLABSCO SUMMARY
Checking the file rather than assuming it is there.
llms.txt is easy to publish and easy to get subtly wrong. This answers both questions an implementer has — does this domain have one, and does it parse — and the list of known compliant sites supplies working examples to measure yours against.
What it is
A server for the llms.txt standard. Give it a domain and it checks for llms.txt and llms-full.txt, reporting where the files are and whether they validate; it also lists known compliant websites as structured data, filterable by which of the two files they publish.
What you get
- A domain checked for llms.txt and llms-full.txt, with file locations and validation status (check_website)
- Known websites publishing llms.txt returned as structured data (list_websites)
- That list filtered by file type — llms.txt or llms-full.txt
- llms.txt contents parsed and validated rather than merely fetched
- Compliant sites also exposed as resources
Requirements
Node, run through npx or a pnpm build of the repository; Smithery installs it in one command. No account and no key.
Setup effort
One command — npx -y @thedaviddias/mcp-llms-txt-explorer
USE CASES
01
Confirming your own site publishes it correctly
The check reports where the files were found and whether the contents validate, so a deploy can be verified rather than assumed.
02
Finding out whether a vendor exposes one
Point it at a domain before building against it, and you know whether there is a machine-readable entry point at all.
03
Finding examples worth copying
The list of known compliant sites gives real files to model yours on, instead of working from the specification alone.
04
Seeing who publishes the full version
Filtering by file type separates sites with llms-full.txt from those with only the short file, which is the difference for anything that needs the whole content.
2 tools
Listed in project docs. Your client may show a different list.
list_websitesBEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation.
Requires
npx on PATH
Where it runs
Both documented setups run the server on your machine.
INSTALLATION
Connect your client
Server setup
Setup
TERMINAL
git clone https://github.com/thedaviddias/mcp-llms-txt-explorer.git
cd mcp-llms-txt-explorer
pnpm install
pnpm run buildAdd the mcpServers entry pointing node at build/index.js (or use the npx form)
npx
TERMINAL
npx -y @thedaviddias/mcp-llms-txt-explorerMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"llms-txt-explorer": {
"command": "node",
"args": [
"<YOUR_PATH_TO_LLMS_TXT_EXPLORER>/build/index.js"
]
}
}
}Claude Desktop — npx
CLAUDE DESKTOP — NPX · JSON
{
"mcpServers": {
"llms-txt-explorer": {
"command": "npx",
"args": [
"-y",
"@thedaviddias/mcp-llms-txt-explorer"
]
}
}
}
