Earshot is a toolkit that lets AI coding agents analyse and describe audio, check how well sound fits a description or a video, and create their own sound effects in code. It runs locally on a CPU as a command-line tool, a Python library or an MCP server.
mcp-figma
by thirdstrandstudio
An MCP server that lets an AI assistant such as Claude Desktop read and work with Figma through the Figma API. It covers files, comments, components, styles, team projects, webhooks and library analytics.
Proof level: ReadWorth a lookMIT
No demo yet
Proof level: Read. We read its README and licence and ran our automatic checks. We have not run it yet. So this page is based on its README and our automatic checks.
The catch
Check this first: Needs a Figma API token, which may be passed on the command line and so be visible in config files or process lists.
Things to check
- Needs a Figma API token, which may be passed on the command line and so be visible in config files or process lists
- Large Figma files may need the depth setting lowered to avoid overloading the assistant
- Some features, such as library analytics, may need a paid Figma plan
Can you use mcp-figma commercially?
Free to use, change and sell, including in paid products. Keep the copyright notice.
Not legal advice. Read the project's licence file before building a product on it.
Did it work for you?
One answer per person for each tool a day, with no account and no cookies. Your answer is remembered in this browser only. How we count
What can you do with mcp-figma?
- Ask an AI assistant to read a Figma file and describe its layout, nodes or components
- Fetch, post and manage comments on Figma files from a chat
- List team projects, styles and components, or set up webhooks for file updates
How do you get mcp-figma running?
Install with npx (or Smithery), or clone the repository and run npm install and npm run build, then add your Figma API token to the Claude Desktop config.
Follow the official instructions in the project README.
Make money with it
A freelancer could offer faster design audits or handover documentation by using an AI assistant to read client Figma files.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Have an AI check design files for components and styles, which cuts the time spent on manual design handover
- Pull Figma comments and file versions into summaries so freelancers can update clients quickly
Checked 07 Nov 2026. Summary drafted by AI from the project's README. Proof level 1 of 4, Read: we read its readme and licence and ran our automatic checks. we have not run it yet.
Similar tools in MCP servers
Kanzo is a small kanban board that runs in your browser and also works as an MCP server, so you and your AI coding agents share the same task list. All data sits in one local folder, which can be synced between machines through a private git repository.
A collection of 77 unofficial MCP servers that let AI assistants search and read Iranian websites such as Digikala, Torob, Divar, Snappfood and Alibaba. It is for comparing prices in Toman, finding jobs, cars, travel, laws and market data from Claude, Cursor or any MCP client.