jmrplensllms.txtgitlab-mcp-server
jmrplens/gitlab-mcp-server/llms.txt
gitlab-mcp-server > A Model Context Protocol (MCP) server that exposes GitLab REST API v4 and GraphQL operations as tools for AI assistants. gitlab-mcp-server v3.1.0 is a single
llms.txt examples
How real projects summarise themselves for language models.
Best matches · from page 18Worked for most · soon
jmrplensllms.txt
mshadmanrahmanllms.txtclaudecode-guide
mshadmanrahman/claudecode-guide/public/llms-full.txt
connecting Claude Code to external tools like GitHub, Slack, Jira, and databases. Think of MCP servers as plugins that give Claude Code access to your other tools. #### MCP Server
mshadmanrahmanllms.txtclaudecode-guide
mshadmanrahman/claudecode-guide/public/llms.txt
Loops](https://claudecodeguide.dev/docs/patterns/autonomous-loops): Run Claude Code unattended with safety controls and task templates. - [MCP Servers](https://claudecodeguide.dev/docs/patterns/mcp-servers): Connect Claude Code to GitHub, Slack, Jira, databases, and external tools
sandraschillms.txtwindows-computer-use-mcp
sandraschi/windows-computer-use-mcp/llms.txt
automation via Pywinauto/UIA — read docs/SAFETY.md. Not a browser agent; not covert surveillance. ## Related MCP servers | Tool | Use for | |------|---------| | **[autohotkey-mcp](https://github.com/sandraschi/autohotkey-mcp)** | Low-level input recording/replay via AHK scripts
anthony-chaudharyllms.txtfak
anthony-chaudhary/fak/llms-full.txt
cache`, `long-session prompt cache`, `cost-aware model routing for agents`, `managed agent runtime`, `MCP tool poisoning defense`, `AI agent least-privilege tool access`, `tamper-evident agent tool-call audit
anthony-chaudharyllms.txtfak
anthony-chaudhary/fak/llms.txt
cache`, `long-session prompt cache`, `cost-aware model routing for agents`, `managed agent runtime`, `MCP tool poisoning defense`, `AI agent least-privilege tool access`, `tamper-evident agent tool-call audit
HorizunGroupllms.txthorizun-revit-mcp
HorizunGroup/horizun-revit-mcp/llms.txt
bridge. Horizun Revit MCP has a public, downloadable Windows installer. The installer includes the MCP server runtime and Revit add-ins. End users do not need Git, Visual Studio
mindcloud-incllms.txtuniversal-api-reference
mindcloud-inc/universal-api-reference/llms.txt
# MindCloud App Reference > Reference documentation for 3219 app APIs (76310 actions), all callable through
rhein1llms.txtagoragentic-integrations
rhein1/agoragentic-integrations/llms-full.txt
agoragentic.com/openapi.yaml | | Agent OS quickstart | https://agoragentic.com/guides/agent-os-quickstart/ | | A2A card (live) | https://agoragentic.com/.well-known/agent-card.json | | MCP server card | https://agoragentic.com/.well-known/mcp/server-card.json | ## Economics And Live Availability - Registration and provider preview are free
rhein1llms.txtagoragentic-integrations
rhein1/agoragentic-integrations/llms.txt
world-agentkit/README.md — experimental World AgentKit pre-payment client; server support remains review-gated - hermes-agent/README.md — Hermes Agent MCP bridge and review-gated self-improvement packet boundary - zoneless/README.md — experimental
agentskillexchangellms.txtskills
agentskillexchange/skills/llms.txt
agentskillexchange.com/skills/build-deterministic-saas-api-test-worlds-for-agents-with-backlot/ ## Collect TikTok and Douyin data through a self-hosted MCP server slug: collect-tiktok-and-douyin-data-through-a-self-hosted-mcp-server category: Research & Scraping framework: MCP
anzy-renlab-aillms.txtpronounce
anzy-renlab-ai/pronounce/docs/llms.txt
underlying source of truth - [GitHub repository](https://github.com/anzy-renlab-ai/pronounce): MIT licensed; PRs welcome - [MCP server](https://github.com/anzy-renlab-ai/pronounce/tree/main/mcp-server): expose the dictionary to any MCP client
bsmi021llms.txtmcp-file-context-server
bsmi021/mcp-file-context-server/docs/llms-full.txt
Each client may support different MCP features, allowing for varying levels of integration with MCP servers. ## Feature support matrix {/* prettier-ignore-start */} | Client | [Resources] | [Prompts] | [Tools] | [Discovery] | [Sampling] | [Roots] | Notes
Microsoftllms.txtforgebook / site
microsoft-foundry/forgebook/site/public/llms.txt
Code (Part 2)](https://microsoft-foundry.github.io/forgebook/notebook/foundry-agent-part-2.md): Connect your agent to Microsoft Learn and GitHub MCP servers, handle MCP approval requests, explore the tool catalog, and see your agent defined
Servosityllms.txtmsp-skills
Servosity/msp-skills/docs/llms-full.txt
Skills - full corpus > Free MCP servers and Skills connecting MSP tools to the AI you already use. Built for MSP business owners. Apache-2.0, runs locally, no data leaves your
Servosityllms.txtmsp-skills
Servosity/msp-skills/docs/llms.txt
Skills > Free MCP servers and Skills that connect your MSP tools (PSA, RMM, backup, M365, and more) to the AI you already use - Claude, ChatGPT, Copilot, Codex, Cursor
booklib-aillms.txtbooklib
booklib-ai/booklib/llms-full.txt
sessions-compare , ` — compare multi-agent audit findings All session data stored in `.booklib/sessions/` (gitignored). --- ## MCP Server Start: `node bin/booklib-mcp.js` Tools exposed: - `search_skills` — semantic search over skill content - `audit_content
lineai-intelligencellms.txtlineai-mcp-server / context
lineai-intelligence/lineai-mcp-server/context/llms-full.txt
5ire is an open source cross-platform desktop AI assistant that supports tools through MCP servers. **Key features:** * Built-in MCP servers can be quickly enabled and disabled. * Users
luuucllms.txtsense
luuuc/sense/docs/llms-full.txt
Sense — Full Documentation > Local MCP server giving AI coding agents structural understanding of a codebase (symbols, relationships, conventions) without reading dozens of files. One binary, one local index, four tools
luuucllms.txtsense
luuuc/sense/docs/llms.txt
Sense > Sense is a local MCP server that gives AI coding agents structural understanding of a codebase (symbols, relationships, conventions) without reading dozens of files. One binary, one local index
About llms.txt
What is llms.txt?
A markdown file at a website's root that gives language models a short guide to the site and links to the pages worth reading.
What's llms-full.txt?
The same idea with the content included, so an agent can read the documentation in one request.
Who reads it?
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
How do I write one?
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.