coolify-mcp
MCP server for Coolify, 42 optimized tools for managing self-hosted PaaS through AI assistants
Runs with mockssource: GitHubhomepageTypeScriptMITcommit a32b0a13bcaa
TypeScript, MIT licensed. The project labels itself: ai, claude, coolify, deployment, devops, infrastructure, mcp and model context protocol.
coolify-mcp runs, with stand-ins for the services it depends on. An Argusic agent installed it in 10.2 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
npm install and tsc build succeed; 1050 unit tests pass; the MCP server initializes over stdio with correct capabilities; doctor CLI verifies all checks against a mock Coolify instance
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- globalThis.crypto.subtle is undefined in Node 18.19.1 — MCP SDK v2's createRequestStateCodec throws on startup and in tests5 minutes
- 3 doctor.test.ts tests fail because they assert runtime status is 'pass', but Node 18 produces 'warn' (expected Node 20+)
- Install time
- 10 minutes
- Cold machine to finish
- 11 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- npm test: 19/20 suites passed, 1050/1053 tests passed (3 doctor failures from Node 18 runtime warning). Server initialization via stdio: responded to JSON-RPC initialize with capabilities and version 3.5.1. Doctor against mock: all 6 checks passed (config, reachability, token, version, abilities, api-shape), only 1 warning (Node 18 runtime).
- Model tokens used
- 274,668
- Exact commit tested
- a32b0a13bcaa
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
-rw-rw-r-- 1 runner runner 132 Oct 17 02:32 jest-setup.mjs
-rw-rw-r-- 1 runner runner 132 Oct 17 02:32 /work/repo/jest-setup.mjs
Let me compile all findings and verify file contents are as expected:
exec
/bin/sh -lc "grep -E '\"start\"|\"test\"' package.json | head -10" in /work/repo
succeeded in 0ms:
"test": "NODE_OPTIONS=\"--experimental-global-webcrypto --experimental-vm-modules\" jest --test…
"start": "NODE_OPTIONS=--experimental-global-webcrypto node dist/index.js",
Now I have all the data. Let me compile the final report.
tokens used
274,668
Now I have all the data. Let me compile the final report.Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 10.2 minutes to install, slower than the median of the 236 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 237 ai projects Argusic has installed and timed, coolify-mcp was the 176th fastest to reach a running state, and 168 of 237 reached one at all.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.05 |
Topics (from GitHub)
aiclaudecoolifydeploymentdevopsinfrastructuremcpmodel-context-protocolpaasself-hostedtypescript
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/coolify-mcp)Questions
- Does coolify-mcp run?
- coolify-mcp runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 10 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test coolify-mcp?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit a32b0a13bcaa. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test coolify-mcp?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does coolify-mcp take to install?
- 10.2 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does coolify-mcp need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing coolify-mcp?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does coolify-mcp compare with the alternatives?
- Of the 237 ai projects Argusic has installed and timed, coolify-mcp was the 176th fastest to reach a running state, and 168 of 237 reached one at all.
- Where is the evidence for coolify-mcp?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.