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 1.5 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
The MCP compatibility proxy builds, installs, and runs as a stdio-to-HTTP proxy, correctly handling initialize, tools/list, auth-failure, and auth-latch scenarios against a local mock server.
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
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
- 2 minutes
- Cold machine to finish
- 3 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- The proxy correctly answered initialize (returned protocolVersion & serverInfo), tools/list (returned tool list), returned auth error -32001 without network when no key provided, and latched auth refusal after receiving a 401 from mock server.
- Model tokens used
- 119,907
- 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
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 3, 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.
Resp 0: id=1, hasResult=false, hasError=true
Resp 1: id=2, hasResult=false, hasError=true
=== AUTH LATCH TEST PASSED ===
exec
/bin/sh -lc 'kill %1 2>/dev/null; kill %2 2>/dev/null; true' in /work/repo
succeeded in 0ms:
All tests passed. Here's the summary:
**ARGUSIC_RESULT:** {"install_succeeded":true,"launch_succeeded":true,"install_minutes":1.5,"errors…
tokens used
119,907
All tests passed. Here's the summary:
**ARGUSIC_RESULT:** {"install_succeeded":true,"launch_succeeded":true,"install_minutes":1.5,"errors…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 1.5 minutes.
- Nothing broke on the way: zero errors between clone and running.
- Licensed ISC, as reported by its host.
- Measured 3 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 3/3 | Runs with mocks | 92.00 | 0.02 | |
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.02 | |
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.01 |
Topics (from GitHub)
21stclaudecursormcpmodel-context-protocolreacttailwindcssui-components
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](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 2 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. 3 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?
- 1.5 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 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 3 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.