fli
Google Flights MCP, CLI and Python Library
Runs with mockssource: GitHubhomepagePythonMITcommit 881aee5ff432
Python, MIT licensed. The project labels itself: api, flights api, google flights, google flights api, mcp and mcp server.
fli runs, with stand-ins for the services it depends on. An Argusic agent installed it in 0.5 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
fli installs cleanly with uv, all 1404 offline tests pass (29 skipped in container config), the CLI parses and displays airport data, the MCP HTTP server starts and serves /health (200) and /mcp/ (307).
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.
- NO_COLOR=1 in container env causes Rich to skip hyperlinks, making test_display_date_results_links_dates_when_route_given fail3 minutes
- uv not pre-installed0.5 minutes
- Install time
- under a minute
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- uv run pytest -v returned 1404 passed, 29 skipped, exit 0; uv run fli airports 'new york' returned 5 airport rows; curl -s http://127.0.0.1:8000/health returned 200; uv run fli --help printed CLI help
- Model tokens used
- 52,531
- Exact commit tested
- 881aee5ff432
- 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.
succeeded in 2756ms:
collecting ... collected 1533 items / 1432 deselected / 101 selected
tests/cli/test_utils.py::test_display_date_results_links_dates_when_route_given PASSED [100%]
====================== 1 passed, 1432 deselected in 1.74s ======================
All verified. Let me produce the final result:
exec
/bin/sh -lc "echo \"{\\\"install_succeeded\\\": true, \\\"launch_succeeded\\\": true, \\\"install_m…
succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 0.5, "errors": [{"msg": "u…
2026-10-01T16:23:07.834275Z ERROR codex_core::session: failed to record rollout items: thread 01a0f…
tokens used
52,531Replay 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 0.5 minutes, faster than the median of the 11 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.
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.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 12 api projects Argusic has installed and timed, fli was the 4th fastest to reach a running state, and 7 of 12 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 | 0.04 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/fli)Questions
- Does fli run?
- fli runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test fli?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 881aee5ff432. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test fli?
- The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does fli take to install?
- 0.5 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 fli need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing fli?
- 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 fli compare with the alternatives?
- Of the 12 api projects Argusic has installed and timed, fli was the 4th fastest to reach a running state, and 7 of 12 reached one at all.
- Where is the evidence for fli?
- 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.