vibe-check-mcp-server

Vibe Check is a tool that provides mentor-like feedback to AI Agents, preventing tunnel-vision, over-engineering and reasoning lock-in for complex and long-horizon agent workflows. KISS your over-eager AI Agents goodbye! Effective for: Coding, Ambiguous Tasks, High-Risk tasks

Runssource: GitHubhomepageTypeScriptMITcommit ed8452f2d626

TypeScript, MIT licensed. The project labels itself: agentic ai, agentic workflow, ai agents, chain of thought, cpi, error handling, mcp and mcp server.

vibe-check-mcp-server runs. An Argusic agent installed it in 16 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

With Node 22.23.3 at /tmp/node22, npm ci and npm run build succeed, all 139 unit tests pass, the MCP server answers 200 on /healthz and handles repeated initialize/tools/list/tools/call requests over HTTP with real LLM responses, and vibe_learn entries persist in ~/.vibe-check/vibe-log.json.

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 100 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.27 (measured)
recorded runs
1
last tested
stars
507
forks
67
open issues
12
watchers
4
size
3 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.

Time lost to each failure while testing vibe-check-mcp-server, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

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

  • Container ships Node v18.19.1 but project requires >=20; vitest 4 crashed on node:util.styleText (rolldown bundler) and npm 9 missed the @rolldown/binding-linux-x64-gnu optional dependency, so the build/tests could not run7 minutes
  • HTTP transport only answered the first request; every subsequent POST to /mcp returned HTTP 500 because the SDK stateless streamable transport throws 'Stateless transport cannot be reused across requests' when one instance is reused6 minutes
  • tests/llm.test.ts 'throws if openrouter key missing' failed: src/utils/llm.ts imported axios dynamically so the vitest mock did not apply (response.data crashed), and the container env OPENROUTER_API_KEY leaked into the test3 minutes
Install time
16 minutes
Cold machine to finish
16 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
npm test exited 0 (139 passed); curl http://127.0.0.1:3000/healthz returned HTTP 200 with {"status":"ok"}; repeated POST /mcp initialize/tools/list/tools/call all returned HTTP 200 with real OpenRouter-generated vibe_check text; node build/cli/index.js --version printed 2.9.0; node build/cli/index.js doctor printed Node.js version v22.23.3 (meets >=20.0.0)
Model tokens used
1,238,183
Exact commit tested
ed8452f2d626
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 1, 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.

/bin/sh -lc 'export PATH=/tmp/node22/bin:$PATH && cd /work/repo && node build/cli/index.js --versio…
 succeeded in 7381ms:
2.9.0
--- final full test run ---
exit=0
      Tests  139 passed (139)
   Start at  16:37:19
   Duration  2.61s (transform 498ms, setup 0ms, import 2.20s, tests 3.11s, environment 2ms)
All final checks pass. Here is my report.
tokens used
1,238,183
All final checks pass. Here is my report.

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.
  • Recovered from all 3 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.

What did not, or is not known

  • Took 16 minutes to install, slower than the median of the 38 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 39 agentic-ai projects Argusic has installed and timed, vibe-check-mcp-server was the 35th fastest to reach a running state, and 31 of 39 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.

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 byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs100.000.27

Topics (from GitHub)

agentic-aiagentic-workflowai-agentschain-of-thoughtcpierror-handlingmcpmcp-servermodel-context-protocolrlivibe-codingworkflow-automation

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/vibe-check-mcp-server.svg)](https://argusic.com/subject/vibe-check-mcp-server)

Questions

Does vibe-check-mcp-server run?
Yes. vibe-check-mcp-server runs. Argusic installed and launched it on a clean machine in 16 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test vibe-check-mcp-server?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit ed8452f2d626. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test vibe-check-mcp-server?
The run that produced this verdict cost $0.27: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does vibe-check-mcp-server take to install?
16 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 vibe-check-mcp-server need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing vibe-check-mcp-server?
3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does vibe-check-mcp-server compare with the alternatives?
Of the 39 agentic-ai projects Argusic has installed and timed, vibe-check-mcp-server was the 35th fastest to reach a running state, and 31 of 39 reached one at all.
Where is the evidence for vibe-check-mcp-server?
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.

Discussion