How real projects summarise themselves for language models.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
dcc-mcpllms.txtdcc-mcp/dcc-mcp-maya/llms.txt
server() -> None ``` ### MayaMcpServer Constructor ```python MayaMcpServer( port: Optional[int] = None, server_name: str = "maya-mcp", server_version: str = "0.9.45", # x-release-please-version gateway_port: Optional[int] = None, registry
karthikrshetllms.txtkarthikrshet/Career-Agents/llms.txt
# Career-Agents LLM Discovery Catalog This file contains the map of available agents, operational
johnxiellms.txtjohnxie/awesome-code-docs/llms-full.txt
skill, discovery, reuse, workflows, composiohq, discover, evaluate, install, contribute, coding, automation, writing, cross ## Awesome MCP Servers Tutorial: Curating and Operating High-Signal MCP Integrations - Path: tutorials/awesome-mcp-servers-tutorial - Index: https://github.com/johnxie/awesome-code-docs/blob/main/tutorials/awesome-mcp-servers-tutorial/README.md
johnxiellms.txtjohnxie/awesome-code-docs/llms.txt
Tutorial: High-Signal Skill Discovery and Reuse for Claude Workflows: https://github.com/johnxie/awesome-code-docs/tree/main/tutorials/awesome-claude-skills-tutorial - Awesome MCP Servers Tutorial: Curating and Operating High-Signal MCP Integrations: https://github.com/johnxie/awesome-code-docs/tree/main/tutorials/awesome-mcp-servers-tutorial - awslabs/mcp Tutorial: Operating
OptimNowllms.txtOptimNow/cloud-finops-skills/llms.txt
Model-agnostic: works with Claude, GPT, Gemini, or any LLM. Also published as an MCP server (`cloud-finops-mcp`) for faceted retrieval. A structured knowledge skill that gives AI agents
GlyphLangllms.txtGlyphLang/GlyphLang/llms.txt
validate ` (add `--ai` for JSON errors), or use the `validate_glyph` tool from the MCP server started by `glyph mcp`. - The complete notation specification follows. --- # GlyphLang Notation Specification **Version
PCIRCLE-AIllms.txtPCIRCLE-AI/toonify-mcp/docs/llms-full.txt
Toonify MCP ============== What it is - Open-source Claude Code plugin and MCP server for local context compression. - Compresses large tool output before it enters the context window, reducing token cost
PCIRCLE-AIllms.txtPCIRCLE-AI/toonify-mcp/docs/llms.txt
/PCIRCLE-AI/toonify-mcp License: MIT Summary - Toonify MCP is a local-first Claude Code plugin and MCP server. - Compresses large JSON, YAML, API responses, and debug output before they enter the context
skaggsxyzllms.txtskaggsxyz/moltstream/llms.txt
start ``` npx moltstream init # configure your agent npx moltstream start # go live on Kick ``` ## MCP Server ``` npx moltstream mcp ``` Exposes 9 tools via stdio MCP protocol: - get_status
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
InsertKoinIOllms.txtInsertKoinIO/koin-skills/llms.txt
diagnose Koin apps. Packaged as the `koin` plugin for Claude Code, with the Kotzilla MCP Server bundled. Install in Claude Code: ``` /plugin marketplace add InsertKoinIO/koin-skills /plugin install koin@koin-skills
QWED-AIllms.txtQWED-AI/qwed-verification/llms.txt
github.com/QWED-AI/qwed-open-responses): agent tool calls, before they run - [qwed-mcp](https://github.com/QWED-AI/qwed-mcp): MCP server for MCP clients - [qwed-a2a](https://github.com/QWED-AI/qwed-a2a): agent-to-agent messages - [qwed
dearlordylordllms.txtdearlordylord/huly-mcp/site/llms.txt
package: https://www.npmjs.com/package/@firfi/huly-cli - Huly CLI documentation: https://github.com/dearlordylord/huly-mcp/tree/master/packages/huly-cli ## Positioning - The maintained Huly MCP server for agent workflows. - Full Huly parity through MCP tools. - LLM-friendly, context-rich programmatic
openSVMllms.txtopenSVM/solana-mcp-server/llms.txt
Solana MCP Server - LLM Documentation ## Overview The Solana MCP Server provides access to Solana blockchain data through the Model Context Protocol (MCP). It implements comprehensive Solana RPC methods organized into
RohanMuppallms.txtRohanMuppa/brightspace-mcp-server/llms.txt
brightspace-mcp-server > MCP server connecting an AI client to D2L Brightspace: grades, assignments, due dates, quizzes, > announcements, syllabus, roster, discussions, and course content. An MCP (Model Context Protocol) server
dcc-mcpllms.txtdcc-mcp/dcc-mcp-blender/llms.txt
Core dep:** `dcc-mcp-core>=0.20.0,<0.21.0` --- ## Quick Start ```python import dcc_mcp_blender server = dcc_mcp_blender.start_server() # Direct MCP host endpoint (OS-assigned); local gateway → http://127.0.0.1:9765/mcp print(server.mcp
michaelbeijerllms.txtmichaelbeijer/Supervertaler/docs/llms.txt
search, and a translation knowledge base to Trados Studio 2024 and 2026 – > plus an MCP server that connects AI assistants to the live Studio session. This is the product site
open-agreementsllms.txtopen-agreements/open-agreements/llms-full.txt
# OpenAgreements > Open, primary-source-backed U.S. legal content — practice guides, 50-state surveys, reviewer
open-agreementsllms.txtopen-agreements/open-agreements/llms.txt
primary categories. ## Optional - [Using OpenAgreements with AI agents & MCP](https://github.com/open-agreements/open-agreements/blob/main/docs/supported-tools.md): local + hosted MCP servers, agent skills, and the CLI for programmatic template filling - [openagreements.org](https://openagreements.org): machine-readable
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
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.
