unifi-mcp

MCP servers & Graph API for the UniFi suite of applications, Network, Protect, and Access

Runs with mockssource: GitHubhomepagePythonMITcommit 466c2f2a538a

Python, MIT licensed. The project labels itself: agentic ai, home automation, mcp server, unifi, unifi access, unifi controller, unifi network and unifi protect.

unifi-mcp runs, with stand-ins for the services it depends on. An Argusic agent installed it in 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.

Whole monorepo installs via uv sync, all 8582 tests across 9 suites pass (core/mcp-shared/catalog/network/protect/access/relay/api/docs), ruff format+lint clean, MCP server starts and registers tools over stdio.

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

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.30 (measured)
recorded runs
2
last tested
stars
1,111
forks
156
open issues
25
watchers
4
size
18 MB
created
last push

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.

Time lost to each failure while testing unifi-mcp, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • network version test fails in shallow checkout without git tags5 minutes
  • ruff binary not installed despite being configured in pyproject.toml1 minute
Install time
2 minutes
Cold machine to finish
24 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
smoke test: uv run --no-sync --package unifi-network-mcp python scripts/smoke_mcp_metadata.py --server network --registration-mode lazy --client-mode auto returned unifi-network-mcp client=auto protocol=2026-07-28 mode=lazy 0.0.1.dev1+g466c2f2a5 UniFi Network Tool Index tools=6 icons=3
Model tokens used
115,392
Exact commit tested
466c2f2a538a
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

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

- core: 2663
- shared: 558
- root tests: 1429
- network: 1360
- protect: 533
- access: 235
- relay: 159
- api: 1564
- docs: 81
Total: 2663+558 = 3221, +1429 = 4650, +1360 = 6010, +533 = 6543, +235 = 6778, +159 = 6937, +1564 = …
Actually wait - the catalog test (1429) includes "10 skipped, 227 subtests passed". The pass count …
OK I'm going to output my final answer now. Single line, plain text. Here it is:

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

  • Installed in 2 minutes, faster than the median of the 38 comparable projects Argusic has measured.
  • 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.
  • Measured 2 times, so the result is not a one-off.

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.

Of the 39 agentic-ai projects Argusic has installed and timed, unifi-mcp was the 16th fastest to reach a running state, and 31 of 39 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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs with mocks92.000.30
Argusic Runner1/3Runs with mocks92.000.12

Topics (from GitHub)

agentic-aihome-automationmcp-serverunifiunifi-accessunifi-controllerunifi-networkunifi-protect

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/unifi-mcp.svg)](https://argusic.com/subject/unifi-mcp)

Questions

Does unifi-mcp run?
unifi-mcp runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 2 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test unifi-mcp?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 466c2f2a538a. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test unifi-mcp?
The run that produced this verdict cost $0.30: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does unifi-mcp take to install?
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 unifi-mcp need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing unifi-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 unifi-mcp compare with the alternatives?
Of the 39 agentic-ai projects Argusic has installed and timed, unifi-mcp was the 16th fastest to reach a running state, and 31 of 39 reached one at all.
Where is the evidence for unifi-mcp?
All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion