How real projects summarise themselves for language models.
floomhqllms.txtfloomhq/floom/llms.txt
loop approval worker. ## Search Keywords AI agents, AI workers, background agents, agent runtime, MCP server, MCP tools, deploy Python script, automation runtime, scheduled AI worker, webhook AI worker, sandboxed
sandraschillms.txtsandraschi/calibremcp/llms-full.txt
github.com/sandraschi/mcp-central-docs/blob/master/standards/MCPB_PACKAGING_STANDARDS.md) · [PACKAGING_STANDARDS.md §5](https://github.com/sandraschi/mcp-central-docs/blob/master/standards/PACKAGING_STANDARDS.md#5-python-mcp-repo-uv-justfile-llmstxt-glama-mcpb-pack) --- ## Tools (representative) Portmanteau-first server (FastMCP 3.1+). Names match MCP registration: - **manage_libraries** — libraries list/switch, stats, connection - **query_books** — search/list with filters, optional
sandraschillms.txtsandraschi/calibremcp/llms.txt
calibre-mcp > FastMCP 3.1+ MCP server for Calibre libraries: portmanteau tools, Calibre FTS, LanceDB metadata + chunk RAG, prompts, bundled skill, optional webapp (**10720** / **10721**). **Full corpus (tools, env, run, troubleshooting
zuke-buildllms.txtzuke-build/zuke/llms-full.txt
string): ProtectedResourceSettings Begin a protected-resource declaration for `resource`, the canonical URI of this MCP endpoint (`https://build.example.com/mcp`). ```ts import { Build, protectedResource } from "@zuke/core"; class CI extends Build { override
zuke-buildllms.txtzuke-build/zuke/llms.txt
Write declared CI configuration files - `completions` — Print a shell-completion script - `mcp` — Run an MCP server over the build (for AI agents) - `resume` — Resume a suspended run (or --check
cloud-ru-techllms.txtcloud-ru-tech/mcp-server-mattermost/llms.txt
Mattermost MCP Server > MCP server providing 37 tools for Mattermost integration: > channels, messages, reactions, threads, users, teams, files, and bookmarks. ## Docs - [Quick Start](https://raw.githubusercontent.com/cloud-ru-tech/mcp-server-mattermost/main/docs/quickstart.md): Installation, local token setup
GoPlausiblellms.txtGoPlausible/algorand-mcp/llms.txt
Developer Tools project_name: algorand-mcp version: 2.7.6 description: Model Context Protocol (MCP) server for Algorand blockchain interactions, providing tools and resources for account management, asset operations, application interactions
ssdeanxllms.txtssdeanx/AgentStack/llms.txt
Model Context Protocol (MCP) - [MCP Client](src/mastra/mcp/mcp-client.ts): Client implementation for MCP - [MCP Index](src/mastra/mcp/index.ts): MCP server entry point ## Networks & Data - [Networks Documentation](src/mastra/networks/AGENTS.md): Documentation for agent networks and routing - [Primary
mcpwarellms.txtmcpware/pagecast/llms.txt
Pagecast > MCP server that turns AI browser interactions into polished product demos — GIF or MP4 with auto-zoom effects. ## Docs - [GitHub](https://github.com/mcpware/pagecast) - [npm](https://www.npmjs.com/package/@mcpware/pagecast) ## Quick Start
bakhtiersizhaevllms.txtbakhtiersizhaev/openevidence-mcp/docs/llms-full.txt
NOTICE ## Product Definition OpenEvidence MCP is an unofficial open-source Model Context Protocol (MCP) server that connects a user's own authenticated OpenEvidence browser session to MCP-compatible AI clients
bakhtiersizhaevllms.txtbakhtiersizhaev/openevidence-mcp/docs/llms.txt
metadata version 0.2.2 continues to use the existing npm package 0.2.1. > Unofficial open-source MCP server for OpenEvidence. Important: this project is not affiliated with OpenEvidence, does not provide medical
crp4222llms.txtcrp4222/PrivAiTe/llms-full.txt
# PrivAiTe, full documentation > Concatenated project documentation for LLM consumption. The map with > one-line
nirholasllms.txtnirholas/universal-crypto-mcp/llms-full.txt
universal-crypto-mcp > Universal MCP server for AI agents to interact with any* blockchain via natural language and plugins. Supports swaps, bridges, gas, staking, lending, and more across Ethereum, Arbitrum
nirholasllms.txtnirholas/universal-crypto-mcp/llms.txt
universal-crypto-mcp > Universal MCP server for AI agents to interact with any* blockchain via natural language and plugins. Supports swaps, bridges, gas, staking, lending, and more across Ethereum, Arbitrum
nirholasllms.txtnirholas/universal-crypto-mcp/x402/llms.txt
cent) - No accounts, sessions, or approval flows - Multi-chain: EVM (Base, Arbitrum, Ethereum) + Solana ## MCP Tools (14 tools) ### Payment Tools - `x402_pay_request` - Make HTTP request with auto-payment - `x402
OnlyCLIllms.txtOnlyCLI/OnlyCLI/docs/llms.txt
wrappers with typed subcommands - Giving AI agents a stable local binary instead of an MCP server - Producing structured stdout for scripts, CI, and automation ## Important product facts - Generated CLIs
oxbshwllms.txtoxbshw/Agent-Span/docs/llms.txt
XiaoHongShu, LinkedIn, Xueqiu, Xiaoyuzhou podcasts, Exa web search, RSS) > through one REST API, CLI, MCP server, and Python SDK. AgentSpan is both a runtime gateway (it serves reads/searches behind
aka-kikallms.txtaka-kika/the-librarian/llms.txt
librarian > A skill librarian MCP server. Agents never load a skill collection into > context: they describe a task in plain language, the librarian recommends the > few skills that fit (local
dcc-mcpllms.txtdcc-mcp/dcc-mcp-blender/llms.txt
server() -> None ``` ### BlenderMcpServer Constructor ```python BlenderMcpServer( port: Optional[int] = None, server_name: str = "blender-mcp", server_version: str = "0.1.20", # x-release-please-version enable_gateway_failover: bool = True, metrics_enabled
jmrplensllms.txtjmrplens/gitlab-mcp-server/llms-full.txt
gitlab-mcp-server. Full Reference > Version 3.1.0 | up to 1094 tools | 34 base meta-tools; 51 self-managed enterprise meta-tools; 52 GitLab.com Enterprise meta-tools | 2 dynamic tools
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.
