mcphub

Self-hosted MCP gateway and control plane for connecting, controlling, and operating MCP servers.

Runssource: GitHubhomepageTypeScriptApache-2.0commit 9cf6c1b8b78f

TypeScript, Apache-2.0 licensed. The project labels itself: mcp, mcp gateway, mcp hub, mcp router and mcp server.

mcphub runs. An Argusic agent installed it in 0.7 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

MCPHub installs, builds, and starts successfully on Node 18.19.1. All 1788 tests pass (211 suites). The server starts on port 3000 and serves GET /health returning 200. The only runtime caveats are missing external dependencies (no uvx, no real API keys for amap/fetch/slack/playwright) and Playwright requiring Node 20+, all of which are expected environment gaps.

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

verdict
Runs
Argusic Score
96 / 100
cost of the verifying run
$0.42 (measured)
recorded runs
2
last tested
stars
2,704
forks
371
open issues
15
watchers
18
size
11 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 mcphub, 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.

  • [email protected] .cjs file uses dynamic import("node:crypto") which triggers ts-jest ESM VM invariant check failure on Node 18 (Error: You need to run with a version of node that supports ES Modules in the VM API)2 minutes
  • mcp_settings.json contained a pre-seeded admin user, causing tests/config/default-settings.test.ts to fail (expected users.length === 0)1 minute
Install time
under a minute
Cold machine to finish
41 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
pnpm backend:build (tsc) exited 0; pnpm test --no-coverage run in 7 batches across all 218 test suites: 211 suites passed, 1788 tests passed, 0 failed; node dist/index.js started on port 3001, GET /health returned 200 with JSON body {'status':'degraded','servers':{'total':4,'connected':0,'disconnected':4}}
Model tokens used
303,480
Exact commit tested
9cf6c1b8b78f
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.

print(f'error2: {error2_minutes}m')
total = install_minutes + error1_minutes + (60*60*60*24*60)  # time for test batches
print(f'Note: tests ran in batches over ~3min wall time')
\"" in /work/repo
 succeeded in 0ms:
install: 0.7m
error1: 2m
error2: 1m
Note: tests ran in batches over ~3min wall time
2026-11-11T02:16:51.486395Z ERROR codex_core::session: failed to record rollout items: thread 01a1c…
tokens used
303,480

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 0.7 minutes, faster than the median of the 15 comparable projects Argusic has measured.
  • 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 Apache-2.0, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

Of the 16 mcp projects Argusic has installed and timed, mcphub was the 6th fastest to reach a running state, and 14 of 16 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.
  • A quick evaluation: it was running 0.7 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 Runner2/3Runs100.000.42
Argusic Runner1/3Runs with mocks92.000.52

Topics (from GitHub)

mcpmcp-gatewaymcp-hubmcp-routermcp-server

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/mcphub.svg)](https://argusic.com/subject/mcphub)

Questions

Does mcphub run?
Yes. mcphub runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test mcphub?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 9cf6c1b8b78f. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test mcphub?
The run that produced this verdict cost $0.42: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does mcphub take to install?
0.7 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 mcphub need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing mcphub?
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.
How does mcphub compare with the alternatives?
Of the 16 mcp projects Argusic has installed and timed, mcphub was the 6th fastest to reach a running state, and 14 of 16 reached one at all.
Where is the evidence for mcphub?
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