magic-mcp

It's like v0, but in your Cursor / Claude Code / Windsurf: search 10,000+ React/Tailwind components, generate new UI with AI, and publish your own, right from your editor. Magic MCP is now the 21st MCP; this package keeps old configs working. Setup: 21st.dev/mcp

Runs with mockssource: GitHubhomepageTypeScriptISCcommit 6e5a43d36214

TypeScript, ISC licensed. The project labels itself: 21st, claude, cursor, mcp, model context protocol, react, tailwindcss and ui components.

magic-mcp runs, with stand-ins for the services it depends on. An Argusic agent installed it in 3 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

The @21st-dev/magic v0.2.2 package installs, builds with TypeScript (dist/index.js), and the stdio-to-HTTP proxy forwards JSON-RPC messages to a configured MCP endpoint with session ID tracking, auth-latching after a 401 response, and no-key short-circuiting.

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

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.02 (measured)
recorded runs
2
last tested
stars
5,919
forks
459
open issues
5
watchers
29
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.

Install time
3 minutes
Cold machine to finish
3 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
Integration test piping JSON-RPC messages through the proxy to a mock 21st.dev MCP server: initialize returned serverInfo, tools/list returned tools, tools/call returned content. Auth latching test (401 response latched for subsequent calls) and no-key short-circuit test also passed.
Model tokens used
44,407
Exact commit tested
6e5a43d36214
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
Behaviour against real services
this run was verified against stand-in services only

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

}
Now I have all the data. Let me compile the final verification summary
exec
/bin/sh -lc 'echo "=== TIMING ===" && date -u && echo "Started around 22:16 UTC, now running final …
 succeeded in 0ms:
=== TIMING ===
Wed Sep 16 22:19:28 UTC 2026
Started around 22:16 UTC, now running final report
All tests pass. Here's the summary.
tokens used
44,407
All tests pass. Here's the summary.

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

  • Installed in 3 minutes.
  • Nothing broke on the way: zero errors between clone and running.
  • Licensed ISC, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.

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 Runner2/3Runs with mocks92.000.02
Argusic Runner1/3Runs with mocks92.000.01

Topics (from GitHub)

21stclaudecursormcpmodel-context-protocolreacttailwindcssui-components

Embed the badge

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

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

Questions

Does magic-mcp run?
magic-mcp runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 3 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test magic-mcp?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 6e5a43d36214. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test magic-mcp?
The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does magic-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 magic-mcp need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing magic-mcp?
Nothing did, in the recorded run: zero errors between clone and running.
Where is the evidence for magic-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