figwright
Free, two-way Figma MCP server. Turn designs into framework-aware code, and push code back to the canvas. Works with Claude Code, Cursor, Codex, and any MCP client.
Runssource: GitHubTypeScriptMITcommit 832b5a358bf4
TypeScript, MIT licensed. The project labels itself: ai, claude code, codegen, codex, cursor, design to code, figma and figma mcp.
figwright runs. An Argusic agent installed it in 8 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
The project installs, builds, and passes all 2162 tests across 210 test files. The MCP server binary at packages/mcp/dist/index.mjs starts and correctly self-identifies as version 0.5.0, binding the leader endpoint on port 3055. All CI gates (typecheck, lint, format, knip, build, test) pass without any errors or warnings.
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
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
- 8 minutes
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- pnpm test exited 0, 210 test files / 2162 tests passed; pnpm build, typecheck, lint, format:check, knip all passed cleanly; MCP server binary starts and reports 'server 0.5.0 (protocol 0.1.0) ready as leader, relay on :3055'
- Model tokens used
- 38,694
- Exact commit tested
- 832b5a358bf4
- 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.
echo \"End time approx 13:25:50 UTC\" # Quick sanity - verify the process-lifecycle e2e test ran (it's the hardest one) grep -l \"SIGSTOP\\|process-lifecycle\" /work/repo/packages/mcp/test/e2e/process-lifecycle.test.ts … succeeded in 0ms: Start time approx 13:17:51 UTC End time approx 13:25:50 UTC /work/repo/packages/mcp/test/e2e/process-lifecycle.test.ts process-lifecycle test exists and ran as part of the suite All done. Let me compile the final report. tokens used 38,694 All done. Let me compile the final report.
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.
- Nothing broke on the way: zero errors between clone and running.
- 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 did not, or is not known
- Took 8 minutes to install, slower than the median of the 236 comparable projects Argusic has measured.
Of the 237 ai projects Argusic has installed and timed, figwright was the 155th fastest to reach a running state, and 168 of 237 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 8 minutes after the clone.
- Following its own README: the documented path worked with nothing to fix.
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
Topics (from GitHub)
aiclaude-codecodegencodexcursordesign-to-codefigmafigma-mcpfigma-pluginfigma-to-codemcpmodel-context-protocol
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/figwright)Questions
- Does figwright run?
- Yes. figwright runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test figwright?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 832b5a358bf4. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test figwright?
- The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does figwright take to install?
- 8 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 figwright need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing figwright?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does figwright compare with the alternatives?
- Of the 237 ai projects Argusic has installed and timed, figwright was the 155th fastest to reach a running state, and 168 of 237 reached one at all.
- Where is the evidence for figwright?
- 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.