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 3 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

package installs in a Python 3.12 venv, CLI commands execute (search returns real arXiv papers, lists 21 sources), MCP server starts on both SSE and Streamable HTTP transports, and 200 of 202 unit tests pass with no code defects.

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

verdict
Runs
Argusic Score
90 / 100
cost of the verifying run
$0.03 (measured)
recorded runs
2
last tested
stars
3,109
forks
308
open issues
20
watchers
7
size
2 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.

What went wrong, in the agent's own words

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

  • test_biorxiv::TestBioRxivSearcher::test_download_and_read failed with HTTP 429 Too Many Requests from bioRxiv.org download endpoint
  • test_semantic::TestSemanticSearcher::test_search_performance_comparison intermittently skipped (performance benchmark, not a correctness failure)
Install time
3 minutes
Cold machine to finish
8 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
python -m pytest tests/ exited with 200 passed, 2 failed (external), 19 skipped, 14 subtests passed; paper-search search 'machine learning' --max-results 2 --sources arxiv returned 2 real papers; paper-search-mcp --transport sse --host 127.0.0.1 --port 8767 started and served on that port; paper-search-mcp --transport streamable-http --host 127.0.0.1 --port 8768 --path /mcp started and served
Model tokens used
72,098
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

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 2, run , the attempt that decided the verdict above. 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.

72,098
Everything works. Let me compile my final report.
Here's the summary:
**Install**: `pip install -e ".[dev]"` in a Python venv — succeeded with all dependencies.
**Launch & verification**:
- CLI: `paper-search --help`, `paper-search-mcp --help` both printed usage
- `paper-search search "machine learning" --max-results 2 --sources arxiv` returned 2 real papers f…
- `paper-search sources` listed 21 available sources
- Server: launched on SSE transport (200 OK, bound to 127.0.0.1:8767)
- Server: launched on Streamable HTTP transport (bound to 127.0.0.1:8768 on /mcp)
**Tests**: 200 passed, 2 failed (1 bioRxiv 429 rate-limit from external API, 1 intermittent skip), …
**Issues found and fixed**: None — no code changes were needed. The only failures were external API…

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 3 minutes.
  • Recovered from all 2 errors 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.

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 3 minutes after the clone.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.03
Argusic Runner1/3Runs80.000.03

Topics (from GitHub)

ai-scientistarxiv-papersmcp-serverpaper-search

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/paper-search-mcp.svg)](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 3 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. 2 attempts are 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?
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 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, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
Where is the evidence for paper-search-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