paper-search-mcp
MCP, CLI, Skills for searching and downloading academic papers from multiple sources like arXiv, PubMed, bioRxiv, etc.
Runssource: GitHubPythonMITcommit 808e462a824c
Python, MIT licensed. The project labels itself: ai scientist, arxiv papers, mcp server and paper search.
paper-search-mcp runs. An Argusic agent installed it in 2 minutes and hit 2 errors on a clean machine with no GPU, and the whole session was recorded.
Package installs, imports, CLI search/results, and MCP server handshake all work. Tests pass modulo transient rate limits from external API servers.
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 80 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.
- HTTP 429 rate limit on bioRxiv PDF download test (test_biorxiv.py::test_download_and_read)
- HTTP 429 rate limit on Semantic Scholar search tests (test_semantic.py: 3 failures)
- Install time
- 2 minutes
- Cold machine to finish
- 9 minutes
- Errors hit and fixed
- 2 hit, 0 fixed with no human help
- How the result was proved
- pytest tests/, 201 passed, 4 failed (all 429 rate limits); paper-search search returned 39 real papers from 13 sources; MCP handshake returns 57 tools
- Model tokens used
- 71,273
- Exact commit tested
- 808e462a824c
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
**Installed**: `pip install -e ".[dev]"` — all deps resolved, 86 packages installed, package built. **Tests**: `pytest tests/` — **201 passed, 4 failed, 16 skipped, 14 subtests passed** in ~91s. All … **CLI**: `paper-search --help` works; `paper-search search "machine learning"` returned 39 real pap… **MCP Server**: Full handshake succeeds — serves **57 MCP tools** (search_papers, search_arxiv, dow… tokens used 71,273 The Semantic Scholar failures are intermittent rate limits — it passes when run individually. All f… Here's the final tally: **Installed**: `pip install -e ".[dev]"` — all deps resolved, 86 packages installed, package built. **Tests**: `pytest tests/` — **201 passed, 4 failed, 16 skipped, 14 subtests passed** in ~91s. All … **CLI**: `paper-search --help` works; `paper-search search "machine learning"` returned 39 real pap… **MCP Server**: Full handshake succeeds — serves **57 MCP tools** (search_papers, search_arxiv, dow…
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 2 minutes.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Hit 2 errors during setup, 2 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
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 2 minutes after the clone.
Run history
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/paper-search-mcp)Questions
- Does paper-search-mcp run?
- Yes. paper-search-mcp runs. 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 paper-search-mcp?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 808e462a824c. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test paper-search-mcp?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does paper-search-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 paper-search-mcp need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing paper-search-mcp?
- 2 things broke in the recorded run. Each one, and the time it cost, is listed on this page.
- Where is the evidence for paper-search-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.