# LLM.txt Directory

> Use this tool when you need to access and search structured documentation for various APIs and services, or integrate up-to-date information into AI models. It solves problems of outdated training data and provides a concise interface for listing, retrieving, and searching documentation files. The LLM.txt Directory server takes in queries and IDs as inputs and returns relevant documentation contents as outputs, making it ideal for developers and AI assistants in need of accurate and timely information.

Canonical page: https://skillsregistry.net/skills/mcp-get-llm-txt  
JSON: https://api.skillsregistry.net/v1/skills/mcp-get-llm-txt

## Description

This LLM.txt MCP server, developed by mcp-get, enables AI assistants to access and search the LLM.txt Directory, a collection of structured documentation files for various APIs and services. Built in TypeScript, it provides tools for listing available LLM.txt files, retrieving their contents, and performing multi-query searches with context. The server implements local caching to improve performance and uses numeric IDs to discourage hallucination of non-existent files. By abstracting access to the LLM.txt ecosystem, this implementation allows AI models to quickly gather accurate information about APIs and services without relying on potentially outdated training data. It is particularly useful for developers and AI assistants needing up-to-date documentation for integrating or troubleshooting various software tools and platforms.

## 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:** 2026-04-29

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/mcp-get-llm-txt)
- **Repository:** <https://github.com/mcp-get/community-servers/tree/HEAD/src/server-llm-txt>

## 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": "mcp-get-llm-txt"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mcp-get-llm-txt` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mcp-get-llm-txt/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