northcinder
Open-source MCP server for comparing products and asking the buyer before purchase.
Runssource: GitHubJavaScriptMITcommit d1343096a7af
JavaScript, MIT licensed. The project labels itself: agentic commerce, human in the loop, local first, mcp, mcp server, model context protocol, privacy and self hosted.
northcinder runs. An Argusic agent installed it in 5 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
On Node 22.14.0, install and release:build complete cleanly, the full test suite (pnpm test) exits 0 with 1197 vitest tests passing, and the local-mode MCP server starts on loopback and serves its tools, reporting version 0.2.1.
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 96 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.
- Container Node is v18.19.1 but the workspace requires Node >=20 (site needs >=22.12) and no root/sudo is available to install a system package4 minutes
- service trust-tranco mtime hot-reload test failed: back-to-back writes get identical mtime on this filesystem, so the lookup saw no change4 minutes
- packages/orders reminder test 'uses the Phoenix buyer-local date' failed under the container's UTC default (expected outcome not_due but code used process-local date)3 minutes
- client readme-links test failed: ENOENT /work/repo/AGENTS.md (file absent from the checkout but required by the test)2 minutes
- Install time
- 5 minutes
- Cold machine to finish
- 19 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- corepack pnpm install --frozen-lockfile (rc 0); corepack pnpm release:build (rc 0); pnpm test exited 0 with 1197 vitest tests passed and northcinder+site node:test suites at 'fail 0'; the local MCP server answered MCP initialize (serverInfo NorthCinder 0.2.1) and tools/list with real tools; northcinder --version printed 'northcinder 0.2.1'
- Model tokens used
- 151,607
- Exact commit tested
- d1343096a7af
- 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.
**Launch (real, not mocked)** - `node northcinder/bin/northcinder.js --version` → `northcinder 0.2.1`. - `northcinder init` → wrote config and printed "Local runtime check: ready on loopback". - Started the MCP server over stdio with the init-printed env; it answered `initialize` (serverInfo… - The standalone `northcinder service` command fails-closed without `NORTHCINDER_API_KEYS` — that i… **Errors recorded and fixed (all 4)** 1. Node too old — fixed with local Node 22.14.0 binary (no system install). 2. `packages/orders` phoenix-timezone test failed in the UTC-default container — fixed by scoping `… 3. `service` trust-tranco mtime hot-reload test failed because back-to-back writes share the same m… 4. Missing root `AGENTS.md` required by `client/test/readme-links.test.ts` — created it with the re… **Verification** - Full `pnpm test` after fixes → rc 0, 15 vitest packages green: 1197 passed (protocol 183, service…
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 5 minutes.
- Recovered from all 4 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 5 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 | 2/3 | Runs with mocks | 92.00 | 0.05 | |
| Argusic Runner | 1/3 | Runs | 100.00 | 0.11 |
Topics (from GitHub)
agentic-commercehuman-in-the-looplocal-firstmcpmcp-servermodel-context-protocolprivacyself-hostedshopping-agenttypescript
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/northcinder)Questions
- Does northcinder run?
- Yes. northcinder runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test northcinder?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit d1343096a7af. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test northcinder?
- The run that produced this verdict cost $0.11: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does northcinder take to install?
- 5 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 northcinder need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing northcinder?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for northcinder?
- 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.