How real projects summarise themselves for language models.
AgentAnycastllms.txtAgentAnycast/agentanycast/llms-full.txt
traversal, peer connections, task state machine, offline message queue, BoltDB persistence, HTTP bridge, and MCP server. ## Repository Structure | Repo | Language | Purpose | |------|----------|---------| | agentanycast | Docs | Main entry, docs, issue tracker | | agentanycast-python
AgentAnycastllms.txtAgentAnycast/agentanycast/llms.txt
mcp_tool(skill) # Skill -> MCPTool card = mcp_tools_to_agent_card("WeatherServer", [tool]) # Wrap MCP server as A2A agent ``` ```typescript import { mcpToolToSkill, skillToMcpTool, mcpToolsToAgentCard } from "agentanycast"; const skill = mcpToolToSkill({ name
AuthPlanellms.txtAuthPlane/authserver/llms.txt
single Go binary. Use it to add MCP-spec-compliant authorization to an MCP server, federate to an existing IdP, broker upstream provider OAuth (GitHub, Slack, Google, Linear, ...), and record
shiqudallms.txtshiquda/roadmap-skill/llms-full.txt
local-first roadmap workspace for humans and AI agents. It combines: - an MCP server for roadmap operations - a local web workspace with Kanban and Graph View - a skill pack
shiqudallms.txtshiquda/roadmap-skill/llms.txt
local-first roadmap workspace for humans and AI agents. It provides an MCP server for roadmap operations, a web workspace with Kanban and dependency graph views, and installable skills
htlin222llms.txthtlin222/openevidence-mcp/docs/llms-full.txt
NOTICE ## Product Definition OpenEvidence MCP is an unofficial open-source Model Context Protocol (MCP) server that connects OpenEvidence browser sessions to MCP-compatible AI clients. ### OpenEvidence Context OpenEvidence is commonly
htlin222llms.txthtlin222/openevidence-mcp/docs/llms.txt
OpenEvidence MCP > Unofficial open-source MCP server for OpenEvidence. ## What It Is - OpenEvidence is used by doctors and clinical teams for evidence-backed medical Q&A. - OpenEvidence MCP connects that
MikkoParkkolallms.txtMikkoParkkola/mcp-gateway/llms.txt
version: 2025-11-25 ## Backend Types - stdio: @anthropic/mcp-server-tavily, @modelcontextprotocol/server-filesystem, etc. - HTTP: any Streamable HTTP MCP server - SSE: Pieces, LangChain, etc. - Capability YAML: any REST API without building an MCP server
sandraschillms.txtsandraschi/inkscape-mcp/llms-full.txt
stdio / HTTP / env bridge) - **REST:** `app.py` mounts on FastMCP HTTP (`/api/health`, `/api/help`, `/api/logs`, …) - **MCPB:** `mcp-server/` tree, `tools/sync_mcpb_src.py`, `tools/pack_mcpb.py` --- ## MCP client snippets ### uv (recommended, repo root) ```json { "mcpServers": { "inkscape-mcp
sandraschillms.txtsandraschi/inkscape-mcp/llms.txt
Inkscape MCP > **Inkscape MCP** is a FastMCP **3.4+** server that drives the **Inkscape CLI** for SVG and vector workflows. Agents use portmanteau tools (`inkscape_file`, `inkscape_vector`, `inkscape_analysis`, `inkscape
vitaecontextllms.txtvitaecontext/vitaecontext/llms-full.txt
install notes, manifests, command wrappers, and extension metadata. - `src/` and `bin/`: CLI and stateless MCP server engine. - `mcp/`: Model Context Protocol documentation, configs, and schema contracts. ## 5. Skill behavior `SKILL.md
vitaecontextllms.txtvitaecontext/vitaecontext/llms.txt
skill maintains an optional deeper local career knowledge graph. A stateless Model Context Protocol (MCP) server provides seamless cross-repository context access. Evidence labels and provider-aware install layouts support
digital-go-jpllms.txtdigital-go-jp/administrative-procedures-mcp/llms.txt
行政手続データ分析 MCP Server (administrative-procedures-mcp) > デジタル庁が公表している行政手続等の棚卸調査結果（約75,000件）を、MCP サーバーと専用 CLI（apcli）で検索・集計するためのツール。Claude Desktop や ChatGPT 等の MCP 対応チャットから自然言語でデータ分析ができる。 データセットは dataset.yaml で定義し（JSON Schema あり）、データ本体はリポジトリに含まれず
corezoidllms.txtcorezoid/corezoid-ai-plugin/public/llms.txt
raw.githubusercontent.com/corezoid/corezoid-ai-plugin/main/plugins/corezoid/skills/marketplace-publish-validation/SKILL.md): Corezoid marketplace pre-publication validator ## MCP Tools The plugin bundles a Go MCP server (`convctl`) with these tools: - **add-chart**: Add a chart to a Corezoid dashboard. chart
mikusnuzllms.txtmikusnuz/meta-ads-mcp/llms.txt
meta-ads-mcp > MCP server for the Meta Marketing API v26.0 — 135 tools for managing Facebook & Instagram ad campaigns, audiences, creatives, insights, catalogs, and more. ## Install ```json { "mcpServers": { "meta
trustablllms.txttrustabl/trustabl/llms.txt
scan, one contract, many artifacts.** A scan inventories every tool, agent, subagent, skill, and MCP server, checks them against the rule packs, and distills the result into one canonical **contract
jonashertnerllms.txtjonashertner/opencaselaw/docs/llms.txt
layer verification architecture closes this gap when an LLM uses our MCP server: 1. Corpus integrity (deterministic decision_id hashing, no fuzzy fallback) 2. Server-built citations (every result carries
alperhankendillms.txtalperhankendi/Ctxo/llms-full.txt
Ctxo MCP Server — Full Reference > AI agents don't fail because they can't code. They fail because they code blind. Ctxo gives them the full picture before they write
alperhankendillms.txtalperhankendi/Ctxo/llms.txt
Ctxo MCP Server > AI agents don't fail because they can't code. They fail because they code blind. Ctxo gives them the full picture before they write a single
alperhankendillms.txtalperhankendi/Ctxo/pages/llms.txt
full picture before they write a single line. Ctxo is a Model Context Protocol (MCP) server that delivers Logic-Slices to AI coding assistants: a symbol plus its transitive dependencies
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.
