# LLMs.txt

> Use this tool when you need to retrieve standardized documentation for Large Language Models in real-time, solving the problem of inconsistent or unavailable model information. It takes website URLs or model identifiers as input and outputs formatted documentation, accessible through multiple interfaces including CLI, MCP Inspector, and Cursor IDE integration. Ideal for LLM development, testing, and deployment scenarios where up-to-date model documentation is crucial.

Canonical page: https://skillsregistry.net/skills/llmtxt  
JSON: https://api.skillsregistry.net/v1/skills/llmtxt

## Description

LLMsTXT Agent is a remote server that provides standardized documentation retrieval for Large Language Models by accessing llms.txt files from websites. It follows a two-tier approach: first checking for documentation at the source website, then falling back to a central repository at llmtxt.dev when primary sources are unavailable. The service delivers real-time documentation updates in a consistent format optimized for LLM consumption, and offers multiple connection methods including MCP Inspector, Cursor IDE integration, and direct CLI access.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/llmtxt)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "llmtxt"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/llmtxt` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/llmtxt/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt