Skip to main content
MCP server CX Codex

LLM Text — MCP server for Claude Code: fetch llms.txt from sites

LLM Text — an MCP server that locates and retrieves llms.txt files from websites. Lets Claude and other AI code assistants read instructions and available tools that a site publishes for them.

no license updated 2026-10-29

Open on GitHub

What LLM Text does

LLM Text works with Claude Code, Codex, Cursor, GitHub Copilot, Windsurf, Cline, Zed, and Gemini CLI. The server searches a website for llms.txt and extracts its contents—typically instructions for AI agents or a list of available tools and models. Handy if you work with a site that explicitly publishes such a file for agent discovery.

The llms.txt standard lets websites tell AI code assistants about their capabilities and requirements. LLM Text simply pulls that information and feeds it into your agent's context.

What it helps with

  • load llms.txt from a site into Claude's context
  • give an agent access to public site instructions
  • auto-discover and use llms.txt when connecting the MCP server

Example prompts for the agent

  • Connect LLM Text and ask your agent: 'Fetch the instructions from llms.txt at example.com'
  • In context: 'What models are available according to this site's llms.txt?'
  • Add the server to your IDE so the agent knows the site's requirements

How to install LLM Text

Install

The MCP registry has no launch command for it: see the repository README

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about LLM Text

What does LLM Text do?

It finds and downloads llms.txt from websites, which typically contains instructions and model info for AI code assistants.

Which platforms support LLM Text?

Claude Code, Codex, Cursor, GitHub Copilot, Windsurf, Cline, Zed, and Gemini CLI.

Do I need to install anything else?

LLM Text is an MCP server that connects through your IDE's configuration. No extra dependencies.

Similar MCP servers

All MCP servers for Agent setup: memory, context, orchestration →
load-llms-txt davila7 load-llms-txt loads external documentation from llms.txt or a custom source and adds project context. Useful when an agent needs reference material during coding. CX Codex +1 239installs llm-context brave llm-context extracts web page text, tables, and code chunks via Brave Search API for LLM grounding. Useful when building agentic RAG workflows. CX Codex +1 1,300installs GEML — a plain-text document format built to be edited in place, one section at a time geml-spec GEML — a plain-text document format built to be edited in place, one section at a time is an MCP server for Claude Code that reads and edits one named section instead of the whole file. CX Codex +1 ★ 31repo stars llm-friendly-context shinpr llm-friendly-context rewrites prompts, handoffs and generated docs so the next agent can see the inputs, the steps and what counts as done. Useful whenever text goes to another model. CX Codex +1 ★ 720repo stars llm-public-opinion-analytics-assistant reason-machines llm-public-opinion-analytics-assistant is a Claude Code skill that crawls trends from 15 platforms, clusters themes, and analyzes sentiment with an LLM. It sends results to Telegram, email, or WeChat. CX Codex +1 2,400installs coding-agent-docs-optimization Samuel Berthe coding-agent-docs-optimization is a Claude Code skill that checks whether an agent can integrate an SDK or API using its documentation alone. It runs for requests about agent-ready docs, llms.txt, or fabricated API calls. CX Codex +1 13,400installs

Project sponsors

Companies that keep this analytics open