Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/jurislm/coolify-mcp/claude-mdgit clone --depth 1 https://github.com/jurislm/coolify-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/jurislm/coolify-mcp/claude-md)<a href="https://agentmods.dev/instructions/jurislm/coolify-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jurislm/coolify-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01868 | $0.01868 |
| Opus 5 | $0.00934 | $0.00934 |
| Sonnet 5 | $0.00374 | $0.00374 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
coolify-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
MCP (Model Context Protocol) server for Coolify that provides 45 token-optimized tools for AI assistants to manage infrastructure through natural language. Tools cover servers, projects, environments, applications, databases, services, deployments, private keys, storages, scheduled tasks, cloud tokens, smart diagnostics, batch operations, and API control. v2.0.0 reduced token usage by 85% (from ~43,000 to ~6,600 tokens) by consolidating related operations into single tools with action parameters.
Commands
bun install # Install dependencies
bun run build # Build TypeScript to dist/
bun run test # Run all tests
bun run lint # Run ESLint
bun run format # Run Prettier
# Run locally
COOLIFY_URL="https://your-coolify.com" COOLIFY_TOKEN="token" node dist/index.js
Architecture
File Structure Pattern
When adding new Coolify API endpoints, follow this order:
- src/types/coolify.ts - Add TypeScript interfaces
- src/lib/coolify-client.ts - Add API client method with explicit return type
- src/lib/mcp-server.ts - Add MCP tool definition
- src/tests/mcp-server.test.ts - Add mocked test
Key Files
- src/index.ts - Entry point, starts MCP server
- src/lib/coolify-client.ts - HTTP client wrapping Coolify REST API
- src/lib/mcp-server.ts - MCP tool definitions and handlers
- src/types/coolify.ts - All Coolify API type definitions
- docs/openapi-chunks/ - OpenAPI spec chunks for reference
Context-Optimized Responses
List endpoints return summaries (uuid, name, status) not full objects. This reduces response sizes by 90-99%. Use get_* tools for full details of a single resource.
Adding New Endpoints
- Verify endpoint exists in
docs/openapi-chunks/ - Add types to
src/types/coolify.ts - Add client method with explicit return type
- Add MCP tool to
src/lib/mcp-server.ts - Add mocked tests (required for codecov coverage)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 170 lines · 1,868 tokens per session scan A 60fcd858ff0c
coolify-mcp CLAUDE.md is an instructions file published in the GitHub repository jurislm/coolify-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,868 tokens to every session, about $0.0093 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
coolify-mcp CLAUDE.md
Claude Code instructions for StuMason/coolify-mcp, covering claude.md, project overview, commands, run locally and evals & red teaming (evals/).
aks-mcp copilot-instructions.md
Copilot instructions for Azure/aks-mcp, covering copilot instructions, project overview, architecture, high-level structure and key components.
infrahub-mcp AGENTS.md
AGENTS.md instructions for opsmill/infrahub-mcp, covering infrahub mcp server, tech stack, file structure, commands and mcp objects.
clum AGENTS.md
AGENTS.md instructions for tddh/clum, covering clum 项目开发规则, mcp 工具使用规则(最高优先级), 开发规范, 项目结构 and 常用命令.
btp-cf-mcp AGENTS.md
Instructions for marianfoo/btp-cf-mcp, covering agents.md, project overview, design principles, build & test and live mcp smoke: mcpurl=… mcpkey=… node test/smoke.mjs.
VCF Orchestrator Agent
Practical operating instructions for AI agents working on the VCF Automation Orchestrator MCP server.