· Joseph · AI & Machine Learning  · 3 min read

Use Figma MCP server with Gemini CLI

In this article, I won't introduce what MCP is. Instead, I will explain how to set up the Figma MCP server and use Gemini as an MCP client to work with Figma. I will also show you how to run a prompt to get a Figma design with Gemini.

TOC

In this article, I won’t introduce what MCP is. Instead, I will explain how to set up the Figma MCP server and use Gemini as an MCP client to work with Figma. I will also show you how to run a prompt to get a Figma design with Gemini.

TOC

Figma MCP Introduction

Unlike other MCP servers that require you to install code to run them, with Figma, you only need to install the latest Figma desktop app and toggle on the MCP server from within the app. The Figma MCP server will then be installed on your host.

install enable MCP

After installation, you can try the link http://127.0.0.1:3845/sse, which should open in your browser with the following result.

localhost

Now that we’ve successfully installed the Figma MCP server, I’ll go ahead and set it up with Gemini.

How to install Gemini? Just check this article: Install Gemini CLI

Setup Gemini and Figma MCP server

If we open Gemini and type /mcp, we should see an empty MCP server list. empty-mcp

Connecting Gemini with the Figma MCP server is quite simple. We just need to add the following setting to ~/.gemini/setting.json or your project’s settings file.

Where is my setting.json? check this tutorial: configuration

  • User settings file:
    • Location: ~/.gemini/settings.json (where ~ is your home directory).
    • Scope: Applies to all Gemini CLI sessions for the current user.
  • Project settings file:
    • Location: .gemini/settings.json within your project’s root directory.
    • Scope: Applies only when running Gemini CLI from that specific project. Project settings override user settings.
  • System settings file:
    • Location: /etc/gemini-cli/settings.json (Linux), C:\ProgramData\gemini-cli\settings.json (Windows) or /Library/Application Support/GeminiCli/settings.json (macOS). The path can be overridden using the GEMINI_CLI_SYSTEM_SETTINGS_PATH environment variable.

Let’s look at my setting.json. After configuring the settings, just type /mcp in the Gemini CLI again, and we’ll see the configured MCP servers.

{
  "theme": "GitHub",
  "selectedAuthType": "gemini-api-key",
  "mcpServers": {
    "Figma Dev Mode MCP": { "url": "http://127.0.0.1:3845/sse" }
  }
}

figma-mcp

So, we’ve connected Gemini with the Figma MCP server, and we can now use Gemini to communicate with Figma.

Communicate With Figma

Before communicating, we have to open Dev Mode on Figma.

  • Design mode:
    • ./before-dev-mode
  • Dev mode:
    • ./after-dev-mode

The final step is to find your Figma file link by right-click > copy link to selection, paste the link into the Gemini CLI, and ask Gemini to do something with a prompt. copy

Let’s try this prompt:

use figma download this link {YOUR_LINK} and save as image.svg

get-image

All done. You can now use Gemini with the Figma MCP server, and you can let Gemini generate frontend code, a backend DB schema, or system user-story documents. Let’s recall what we’ve done:

  1. install the Figma app,
  2. toggle on the Figma MCP server in the app,
  3. use Dev mode,
  4. set the Gemini mcpServers setting,
  5. get the Figma file link, and
  6. prompt Gemini.

If you like this post, please connect with me on LinkedIn and give me some encouragement. Thanks.

Back to Blog

Related Posts

View All Posts »
Use Grafana MCP with Gemini and n8n

Use Grafana MCP with Gemini and n8n

The Model Context Protocol (MCP) is extremely useful. An AI assistant helps you decide when and how to use connected tools, so you only need to configure them. After integrating MCP logging management systems into several of my projects, it has saved me a significant amount of time. In this article, I'm going to integrate Grafana with the Gemini CLI and n8n. I will chat with the Gemini CLI and n8n and have them invoke the Grafana MCP server. structure TOC

Install Gemini CLI

Install Gemini CLI

Introduction Gemini CLI has been one of the most popular AI agents in the first half of 2025. It's similar to Claude Code, bringing its power directly into your terminal. Although other terminal AI agents exist, their pricing plans are quite different. Gemini CLI provides a free tier with 100 requests per day using Gemini 2.5 Pro, and you can unlock Tier 1 by upgrading to a paid plan. Prerequisites I'm going to use npm to install Gemini. My Node.js version is v24.4.1, and my npm version is 11.4.2. Gemini needs Node.js version 20 or higher installed. If you're using macOS, you can also choose Homebrew to install the Gemini CLI. Installation Now, let's install it using npm. After installation, you can run gemini directly in your terminal. npm install -g @google/gemini-cli installation I'm using the Use Gemini API key authentication method, so I need to generate a key from Google AI Studio and set it in .zshrc (or .bashrc) by adding this line: And then you can try Gemini now! Run some examples example Prompt: give me suggestions for the socket functionality of this project? Response: Conclusion: The Gemini installation is very simple. Although I am using Neovim with Avante, Gemini gives me more power to use the terminal. Next, I will explore how to use Gemini with an MCP server and integrate the workflow into my daily tasks.

AI code review with n8n

AI code review with n8n

Previously I read a post "Automate and Accelerate GitLab Code Reviews with OpenAI and n8n.io". This made me wonder: If I don’t choose GitHub Copilot for code reviews, can I still integrate AI and n8n with GitHub PR reviews? I haven’t written a blog in a long time—it’s time to start again!

Use ChatGPT to translate new react-dev doc

Use ChatGPT to translate new react-dev doc

react.dev was released on March 17. I've read the beta version for a while. I love the Escape Hatches section which has many correct and recommended usages about react hooks. After new react.dev released, I noticed that there's no translation. I haven'n played OpenAI API yet, so I think this is a good opportunity to play ChatGPT with its translation feature for react.dev. TOC