How real projects summarise themselves for language models.
MrPunyapalllms.txtMrPunyapal/laravel-auditor/docs/llms.txt
focused verification and DSA reviews. - https://mrpunyapal.github.io/laravel-auditor/mcp: Register the Laravel Auditor stdio MCP server and the structured context tools it exposes. - https://mrpunyapal.github.io/laravel-auditor/rules: The evidence-first audit catalog
ofershapllms.txtofershap/real-browser-mcp/llms.txt
real-browser-mcp > Local MCP server + Chrome extension that connects AI coding agents to the user's real Chrome: existing tabs, cookies, SSO, and logins. Not a headless browser
ariffazilllms.txtariffazil/arifOS/llms.txt
machine decision metrics ## A2A Protocol — Peer-to-Peer Collaboration In addition to MCP (which handles direct client-server data and tool access), the arifOS federation utilizes the **Agent-to-Agent
ariffazilllms.txtariffazil/arifOS/static/llms-full.txt
SEAL = all floors passed. See Nine-Signal doctrine for Dwibahasa label semantics. - `status: healthy`: MCP server is responding. Does not certify individual tool accuracy. --- ## Tool Namespace Exposure **Current public tool
assafkipllms.txtassafkip/huntkit/llms.txt
structured analytic techniques (Heuer / CIA tradecraft primer), chain-of-custody evidence capture, and bundled MCP servers for infrastructure recon and threat intel. huntkit is a Claude Code plugin that turns
sandraschillms.txtsandraschi/blender-mcp/llms-full.txt
PYTHON_DEPENDENCY_HELL_FIX.md) **The Great Python 3.13 Catastrophe of October 2025** - How Python 3.13 broke all MCP servers - The fix (version constraints) - Quick reference card - "Dependency hell was not invented
davidmosiahllms.txtdavidmosiah/google-health-mcp/docs/llms.txt
Google Health MCP Unofficial Unofficial local-first MCP server for Google Health API v4. Important tools: google_health_connection_status, google_health_data_inventory, google_health_data_type_coverage, google
davidmosiahllms.txtdavidmosiah/google-health-mcp/llms.txt
Google Health MCP Unofficial local-first Google Health API v4 MCP server for AI health, sleep and activity agents. Repository: https://github.com/davidmosiah/google-health-mcp Homepage: https://wellness.delx.ai/connectors/google-health NPM: https://www.npmjs.com
enessarillms.txtenessari/metabase-ai-assistant/llms.txt
metabase-ai-assistant > Enterprise-grade Model Context Protocol (MCP) Server for Metabase Business Intelligence with 143 dedicated tools, native dbt Semantic Layer integration, Governance-First business memory, autonomous self-healing
remete618llms.txtremete618/widemem-ai/llms.txt
default, and the tradeoff - [API reference](docs/api.md): WideMemory methods and the core types - [MCP server](docs/mcp.md): run widemem as a Model Context Protocol server for agents ## Concepts - [Scoring and decay
undergroundrapllms.txtundergroundrap/UEFN-TOOLBELT/llms.txt
same-user clients. That is Toolbelt's own > surface, not Epic's official UEFN MCP server. ## What this is UEFN Toolbelt is an open-source (AGPL-3.0) tool suite
Agent360dkllms.txtAgent360dk/browser-mcp/docs/llms.txt
Chrome extension - from the Chrome Web Store, or loaded unpacked. (2) A local MCP server, registered with the client. Neither half installs the other: Chrome forbids extensions self-installing from
vstorm-collms.txtvstorm-co/agenticos/llms.txt
Reaches hardware through drivers.** One interface to 27 model providers and to any MCP server by URL. Changing a model profile moves every agent using it, without republishing
dcc-mcpllms.txtdcc-mcp/dcc-mcp-core/llms-full.txt
compression ├── dcc-mcp-capture/ # Screen/window capture ├── dcc-mcp-usd/ # USD scene bridge ├── dcc-mcp-server/ # Binary entry point, gateway runner ├── dcc-mcp-logging/ # Rolling file logging ├── dcc-mcp-paths/ # Platform
dcc-mcpllms.txtdcc-mcp/dcc-mcp-core/llms.txt
skill(activate_groups=false)` + `activate_tool_group(group_name=...)` for lazy activation | | Remote-accessible MCP server (cloud agents) | `create_skill_server("maya", McpHttpConfig(host="0.0.0.0", port=8765, enable_cors=True
Naridon-Incllms.txtNaridon-Inc/aura/llms.txt
multiple agents work it in parallel without colliding on the same symbols. ## Agent integration - MCP server: `{"mcpServers": {"aura-vcs": {"command": "aura", "args": ["mcp"]}}}` exposes 30+ tools, including `aura_log_intent
sema-lispllms.txtsema-lisp/sema/playground/llms.txt
topic. - [Model Context Protocol](https://sema-lang.com/docs/mcp): install and use the native `sema mcp` server, including notebook and user-defined `deftool` tools. - [AI Catalog](https://sema-lang.com/.well-known/ai-catalog.json): canonical machine-readable
video-dbllms.txtvideo-db/agent-toolkit/context/llms-full.txt
# Task --- You are an advanced assistant specialized in generating VideoDB Python code. You have
aeoessllms.txtaeoess/agent-passport-system/llms.txt
Cursor instruction-injection class - GHSA-vqv7-vq92-x87f: Cursor MCP / rules surface - CurXecute: Cursor MCP server config-mutation chain - NomShub: instruction-class file planting against agent IDEs In each case
buriedsignalsllms.txtburiedsignals/spotlight/llms.txt
fetch` and `search` are backed by `firecrawl`. - `query-vault` is backed by the OpenKnowledge MCP server for the configured workspace. - `vault-write` is backed by the OpenKnowledge MCP server with
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.
The same idea with the content included, so an agent can read the documentation in one request.
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.
