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 skills add StuMason/coolify-mcp --skill coolifygit clone --depth 1 https://github.com/StuMason/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/skills/stumason/coolify-mcp/coolify)<a href="https://agentmods.dev/skills/stumason/coolify-mcp/coolify"><img src="https://agentmods.dev/badge/skills/stumason/coolify-mcp/coolify/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/stumason/coolify-mcp/coolify"><img src="https://agentmods.dev/badge/skills/stumason/coolify-mcp/coolify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 123 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- low Excessive Agency · line 3 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 5.1 | $0.00156 | $0.02194 |
| Opus 5.5 | $0.00062 | $0.00878 |
| Sonnet 5.5 | $0.00031 | $0.00439 |
| Haiku 4.5 | $0.00016 | $0.00219 |
Grade A, and why
coolify scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Use it for any user request that touches a Coolify-managed resource, even when the user phrases the request in product terms ("redeploy the API", "restart postgres", "check why staging is unhealthy") rather than naming C How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coolify MCP Skill
This skill teaches Claude how to use the Coolify MCP server (@masonator/coolify-mcp) effectively. The server exposes ~38 token-optimized tools that wrap the Coolify API for managing self-hosted apps, databases, services, and infrastructure.
When to use this skill
Use it for any user request that touches a Coolify-managed resource, even when the user phrases the request in product terms ("redeploy the API", "restart postgres", "check why staging is unhealthy") rather than naming Coolify explicitly. If a Coolify MCP tool exists for the job, prefer it over curl, the Coolify HTTP API directly, SSH, or generic shell access — the MCP tools return summarized, token-cheap responses and include _actions hints for the natural next step.
If the Coolify MCP server is not configured in the current session, tell the user how to install it (see "Setup" below) instead of guessing.
Mental model
Coolify resources form a hierarchy: Server → Project → Environment → (Application | Database | Service). Most "smart lookup" tools accept either a UUID or a human-friendly identifier (name, domain, IP), so you usually don't need to look up UUIDs first. Start broad (get_infrastructure_overview, find_issues) and narrow down with diagnose_app / diagnose_server before taking action.
The API splits "list" (cheap, summarized) from "get" (full detail). Always start with a list/overview call and only fetch full details for the specific resource you care about — this keeps responses small and fast.
Core workflow
- Orient. If you don't already know the relevant resource, call
get_infrastructure_overview(one call returns a summary of everything) orfind_issues(scans for unhealthy resources). For a known target, jump straight todiagnose_appordiagnose_server. - Diagnose before acting. For application problems,
diagnose_app <name|domain|uuid>returns status, recent logs, env vars, and deployment history in one shot. Read it before restarting or redeploying — the cause is often visible there. - Act. Use
controlto start/stop/restart,deployto trigger a build,application/database/servicefor CRUD, andenv_varsfor environment variables. - Verify. After a deploy or restart, call
deploymentfor status, thenapplication_logs(ordiagnose_appagain) to confirm the resource came back healthy. - Report back. Summarize what you changed, link the resource by name, and surface anything from
_actionsthat the user might want to do next.
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.
- 1mo ago Changed 8945b946d9dc
- 1mo ago First seen · 148 lines · 156 tokens per session scan A 050b1f4555f7
coolify is a skill published in the GitHub repository StuMason/coolify-mcp (616 stars, last pushed 2d ago), licensed MIT. It adds 156 tokens to every session and 2,194 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
coolify-setup
Run MCP setup preflight and wire Coolify project/environment/server linkage. Use when onboarding a new workspace or linking an existing Coolify project.
coolify-deploy
Deploy a Coolify application and monitor until terminal status. Use when triggering deployments or watching build progress.
api-workers
Cloudflare Workers deployment using createWorkerHandler from @cyanheads/mcp-ts-core/worker. Covers the full handler signature, binding types, CloudflareBindings extensibility, runtime compatibility guards, and wrangler.toml requirements.
discovery-patterns
Configure ServiceNow Discovery — schedules, IP ranges, credential affinities, MID Server assignment, custom probes/sensors, identification rules, and run-status monitoring on discovery tables.
coolify
Use when self-hosting apps and databases with Coolify on a VPS you own — install, first-admin lockdown, Git-to-deploy (Nixpacks/Dockerfile/compose), managed Postgres/Redis, scheduled S3 backups, domains + auto-SSL. NOT a PaaS someone else runs (that is railway), NOT sizing/hardening the box (that is hetzner), NOT…
tailscale
This skill should be used when managing Tailscale mesh VPN networks. Use when the user asks to "check tailscale status", "list tailscale devices", "ping a device", "send file via tailscale", "tailscale funnel", "tailscale serve", "create auth key", "check who's online", "tailscale exit node", "Magic DNS", or mentions…