MCP-Nest

A NestJS module to effortlessly create Model Context Protocol (MCP) servers for exposing AI tools, resources, and prompts.

Runssource: GitHubTypeScriptMITcommit 3c5531dc3f56

TypeScript, MIT licensed. The project labels itself: llm, llms, mcp, mcp nest, model context protocol, modelcontextprotocol and nestjs.

MCP-Nest runs. An Argusic agent installed it in 1 minute and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Both packages build successfully (tsc), all 930 unit tests pass, and 251 e2e integration tests pass covering tools, resources, prompts, strategies, modern-era (2026-07-28) and legacy-era MCP protocol serving, guards, dynamic registration, and streamable HTTP transport.

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
$0.12 (measured)
recorded runs
1
last tested
stars
733
forks
125
open issues
14
watchers
10
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.

Time lost to each failure while testing MCP-Nest, 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.

  • bun not found in container; required by build and test scripts2 minutes
Install time
1 minutes
Cold machine to finish
12 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
npm test (via bun) exited 0: 930 pass, 0 fail across 59 files; additionally 251 e2e specs pass across 11 files (tools, resources, prompts, strategies, modern-era protocol, dynamic registration, streamable controllers)
Model tokens used
90,853
Exact commit tested
3c5531dc3f56
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.

/bin/sh -lc 'export PATH="$HOME/.local/bin:$PATH" && cd /work/repo && bun test tests/mcp-tool.e2e.s…
 succeeded in 5273ms:
 251 pass
 0 fail
 628 expect() calls
Ran 251 tests across 11 files. [5.40s]
All 975 tests pass across 14 files (930 unit + 251 e2e). Let me compile the final result.
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 1, "er…
tokens used
90,853
All 975 tests pass across 14 files (930 unit + 251 e2e). Let me compile the final result.
**ARGUSIC_RESULT:** {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 1, "er…

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 1 minute.
  • Recovered from all 1 error 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

  • 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 1 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 byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs100.000.12

Topics (from GitHub)

llmllmsmcpmcp-nestmodel-context-protocolmodelcontextprotocolnestjs

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/MCP-Nest.svg)](https://argusic.com/subject/mcp-nest)

Questions

Does MCP-Nest run?
Yes. MCP-Nest runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test MCP-Nest?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 3c5531dc3f56. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test MCP-Nest?
The run that produced this verdict cost $0.12: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does MCP-Nest take to install?
1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does MCP-Nest need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing MCP-Nest?
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.
Where is the evidence for MCP-Nest?
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