python-sdk
The official Python SDK for Model Context Protocol servers and clients
Runssource: GitHubhomepagePythonMITcommit d060b36e1d09
Python, MIT licensed. The project labels itself: mcp, mcp client, mcp server and python.
python-sdk runs. An Argusic agent installed it in 0.0 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The MCP Python SDK v2 installs, builds, and all 5879 tests pass with either uv run --frozen pytest -n auto or by running test groups individually. The package is ready for use as an MCP server/client library.
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 90 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.
- FreePortFactory in anyio pytest_plugin hangs when IPv6 loopback (::1) cannot bind but socket.has_ipv6 is True15 minutes
- Install time
- under a minute
- Cold machine to finish
- 43 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- Model tokens used
- 517,267
- Exact commit tested
- d060b36e1d09
- 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.
- How the result was proved
- runs before 2026-09-07 did not record the command used to check the result
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
+ UV_FROZEN=1 + uv run --frozen strict-no-cover strict-no-cover v0.1.1 ✅ No lines wrongly marked with 'pragma: no cover' The coverage run hangs too. Coverage overhead plus tests takes time but it shouldn't be 30 seconds … Let me record 2026-09-05T21:02:27.483330Z ERROR codex_core::session: failed to record rollout items: thread 01a07… 2026-09-05T21:02:27.483858Z ERROR codex_core::session: failed to record rollout items: thread 01a07… tokens used 517,267 The coverage run hangs too. Coverage overhead plus tests takes time but it shouldn't be 30 seconds … Let me record
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
- Reached a running state on a clean machine, with the session recorded.
- Installed in 0.0 minutes, faster than the median of the 3 comparable projects Argusic has measured.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
Of the 4 mcp projects Argusic has installed and timed, python-sdk was the 1st fastest to reach a running state, and 3 of 4 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 0.0 minutes after the clone.
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 | 100.00 | 0.26 | |
| Argusic Runner | 1/3 | Unverified | 80.00 | 0.01 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/python-sdk)Questions
- Does python-sdk run?
- Yes. python-sdk runs. Argusic installed and launched it on a clean machine in 0 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test python-sdk?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit d060b36e1d09. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test python-sdk?
- The run that produced this verdict cost $0.26: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does python-sdk take to install?
- 0.0 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 python-sdk need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing python-sdk?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does python-sdk compare with the alternatives?
- Of the 4 mcp projects Argusic has installed and timed, python-sdk was the 1st fastest to reach a running state, and 3 of 4 reached one at all.
- Where is the evidence for python-sdk?
- 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.