cursor-talk-to-figma-mcp

TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.

Runs with mockssource: GitHubhomepageJavaScriptMITcommit ddd90f3a6d45

JavaScript, MIT licensed. The project labels itself: agent, agentic, agentic ai, ai, ai agents, automation, claude code and codex.

cursor-talk-to-figma-mcp runs, with stand-ins for the services it depends on. An Argusic agent installed it in 6 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

Dependencies installed, the project builds with tsup, the WebSocket relay starts on port 3055, and the MCP server starts on stdio, initializes, connects to the relay, and responds to all MCP protocol messages (initialize, tools/list, prompts/list, tools/call).

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

At a glance

verdict
Runs with mocks
Argusic Score
56 / 100
cost of the verifying run
$0.03 (measured)
recorded runs
2
last tested
stars
7,031
forks
776
open issues
88
watchers
43
size
7 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
6 minutes
Cold machine to finish
8 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
Model tokens used
80,026
Exact commit tested
ddd90f3a6d45
Container image
sha256:4c3d41857be3

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.

How the result was proved
runs before 2026-09-07 did not record the command used to check the result
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.

 succeeded in 0ms:
total 484
drwxr-xr-x 2 runner runner   4096 Sep  3 16:21 .
drwxr-xr-x 8 runner runner   4096 Sep  3 16:21 ..
-rwxr-xr-x 1 runner runner  86667 Sep  3 16:21 server.cjs
-rw-rw-r-- 1 runner runner 149880 Sep  3 16:21 server.cjs.map
-rw-rw-r-- 1 runner runner     20 Sep  3 16:21 server.d.cts
-rw-rw-r-- 1 runner runner     20 Sep  3 16:21 server.d.ts
-rwxr-xr-x 1 runner runner  83592 Sep  3 16:21 server.js
-rw-rw-r-- 1 runner runner 149835 Sep  3 16:21 server.js.map
tokens used
80,026

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 6 minutes, faster than the median of the 32 comparable projects Argusic has measured.
  • Nothing broke on the way: zero errors between clone and running.
  • 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

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

Of the 33 agent projects Argusic has installed and timed, cursor-talk-to-figma-mcp was the 17th fastest to reach a running state, and 25 of 33 reached one at all.

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 Runner2/3Did not run20.000.13
Argusic Runner1/3Runs with mocks92.000.03

Topics (from GitHub)

agentagenticagentic-aiaiai-agentsautomationclaude-codecodexcursordesignfigmagenerative-aillmllmsmcpmodel-context-protocol

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/cursor-talk-to-figma-mcp.svg)](https://argusic.com/subject/cursor-talk-to-figma-mcp)

Questions

Does cursor-talk-to-figma-mcp run?
cursor-talk-to-figma-mcp runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 6 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test cursor-talk-to-figma-mcp?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit ddd90f3a6d45. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test cursor-talk-to-figma-mcp?
The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does cursor-talk-to-figma-mcp take to install?
6 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 cursor-talk-to-figma-mcp need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing cursor-talk-to-figma-mcp?
Nothing did, in the recorded run: zero errors between clone and running.
How does cursor-talk-to-figma-mcp compare with the alternatives?
Of the 33 agent projects Argusic has installed and timed, cursor-talk-to-figma-mcp was the 17th fastest to reach a running state, and 25 of 33 reached one at all.
Where is the evidence for cursor-talk-to-figma-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