zotero-mcp
Zotero MCP: Connects your Zotero research library with Claude and other AI assistants via the Model Context Protocol to discuss papers, get summaries, analyze citations, and more.
Runs with mockssource: GitHubhomepagePythonMITcommit 075cf2c59842
Python, MIT licensed. The project labels itself: ai agent, chatgpt, claude, claude code, mcp, mcp server, model context protocol and research tools.
zotero-mcp runs, with stand-ins for the services it depends on. An Argusic agent installed it in 3 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 Python package installs and builds; 3785 unit tests pass; both the MCP server and CLI entry points launch and print their version/help banner; the server serves on stdio transport without crash.
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.
- test_download_attachment_file_falls_back_to_webdav failed: test_stringified_params.py pollutes ZOTERO_LOCAL env var globally, causing is_local_mode() to return True and adding an extra 'Local storage: ...' error before the expected 'Local Zotero: not available'5 minutes
- Install time
- 3 minutes
- Cold machine to finish
- 22 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- pytest tests/ --ignore=tests/live --tb=line -q exited 0, 3785 passed, 1 skipped
- Model tokens used
- 132,470
- Exact commit tested
- 075cf2c59842
- 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.
Here's my final assessment: - **Install**: Python virtualenv + `pip install -e ".[dev]"` completed successfully. All 350+ depen… - **Fix needed**: One test failed due to cross-test environment pollution — `test_stringified_param… - **Tests**: 3785 passed, 1 skipped, 19 warnings (all deprecation warnings from FastMCP's logging A… - **Launch**: `zotero-mcp serve` starts the MCP server via stdio transport; `zotero-mcp version` pr… tokens used 132,470 Here's my final assessment: - **Install**: Python virtualenv + `pip install -e ".[dev]"` completed successfully. All 350+ depen… - **Fix needed**: One test failed due to cross-test environment pollution — `test_stringified_param… - **Tests**: 3785 passed, 1 skipped, 19 warnings (all deprecation warnings from FastMCP's logging A… - **Launch**: `zotero-mcp serve` starts the MCP server via stdio transport; `zotero-mcp version` pr…
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 3 minutes, faster than the median of the 81 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.
- 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 82 ai-agent projects Argusic has installed and timed, zotero-mcp was the 29th fastest to reach a running state, and 58 of 82 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 | 2/3 | Runs with mocks | 92.00 | 0.24 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.11 |
Topics (from GitHub)
ai-agentchatgptclaudeclaude-codemcpmcp-servermodel-context-protocolresearch-toolssemantic-searchzoterozotero-plugin
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/zotero-mcp)Questions
- Does zotero-mcp run?
- zotero-mcp runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 3 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test zotero-mcp?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 075cf2c59842. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test zotero-mcp?
- The run that produced this verdict cost $0.24: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does zotero-mcp take to install?
- 3 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 zotero-mcp need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing zotero-mcp?
- 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 zotero-mcp compare with the alternatives?
- Of the 82 ai-agent projects Argusic has installed and timed, zotero-mcp was the 29th fastest to reach a running state, and 58 of 82 reached one at all.
- Where is the evidence for zotero-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.