Figma Mcp Express

io.github.sunhome243Published by GitHub account sunhome243v2.8.1Updated Oct 24, 2026

Compact Figma MCP with validated batch ops through a local plugin bridge.

The publisher's own server: Figma MCP Server

VerifiedSTDIODesktop onlyDeveloper ToolsMedia & Design

Overview

AI-generated overview

A compact Figma MCP server that enables AI agents to read, edit, and prototype directly within the Figma Desktop application.

What you can do
Allows agents to interact with the Figma Desktop file by reading and modifying live elements such as nodes, components, variables, and styles. It supports batch operations, multi-file routing, and prototype wiring. Agents can perform tasks like design system migrations, large file audits, and prompt-to-Figma workflows directly in the design environment.
When to use it
Use this server when AI agents need to perform complex, real-time design tasks within the actual Figma Desktop file, going beyond simple screenshots or comments. It is ideal for design system migrations, large-scale audits, and advanced prompt-to-design workflows.
Requirements
Runs as a local process on the user's machine. For REST-only operations like fetching library catalogs, the FIGMA_TOKEN environment variable is required. Installation can be done via npm or by building from source.
Before you install
The FIGMA_TOKEN acts like a password and should never be committed to version control. Live read/write tools interact directly with the Figma Desktop plugin, and plugin execution is single-threaded per file.

Installation

In SourceWeft

  1. Open Figma Mcp Express in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

figma-mcp-express

[Figma MCP Express hero: the fast lane for AI agents into Figma]

[License: MIT] [Go] [npm] [Works with Claude Code] [Works with Codex]

Fast, quota-free, stable Figma automation for coding agents. figma-mcp-express lets Claude Code, Codex, and other local agents read, edit, migrate, audit, screenshot, and prototype inside the real Figma Desktop file. It is built for serious design-system work: batch edits, multi-file routing, large-file reads, visible multi-agent activity, and prototype wiring without burning through official Figma MCP tool-call quotas.

Use it when screenshots and comments are not enough. The agent can inspect actual nodes, components, variables, styles, frames, prototype reactions, and connected files, then make targeted changes in the file designers already use.

Demo

[Multiple AI agents building screens live in Figma]

Watch the demo video

Follow AI agents live as they fix issues, edit layouts, and design screens directly in Figma.

Why teams use it

  • More automation, fewer quota walls. Normal plugin-side work is not capped by the official Figma MCP server's seat-based tool-call limits.
  • Compact tool surface. Compared with vkhanhqui/figma-mcp-go@fe6cd768 (the intermediate fork baseline used for this measurement), the default tools/list drops from 73 tools / 12,214 o200k_base tokens to 21 tools / 3,283 tokens (73.1% smaller) — less context burned before the agent does any work.
  • Real Figma context, not screenshots. Agents work with live nodes, components, variables, styles, frames, screenshots, and prototype links in the open Desktop file.
  • Built for design-system migration. Route a source library and product file through separate channels, then rebuild screens with the right components and tokens.
  • Made for multi-agent runs. Watch agent activity live, follow one agent's edits, and keep file sessions separated by channel.
  • Large files stay usable. Big reads spill to disk so agents can inspect only the useful slice instead of flooding the model context.
  • Prototype automation is part of the workflow. Read prototype flows, set reactions, and set flow starting points.

Capabilities

  • Watch live agent activity in the Figma plugin.
  • Build polished Figma screens with built-in AI agent skills.
  • Route multiple open files through separate channels.
  • Migrate design systems with real components, variables, and styles.
  • Read and wire prototype flows directly in the open Figma file.

Good fit

  • Design system migrations and component-library swaps
  • Large file audits, cleanup, and token rebinding
  • Design-to-code handoff that needs real token and component context
  • Prompt-to-Figma workflows that should use your actual library instead of raw shapes
  • Prototype audits and wiring for navigation, overlays, transitions, and flow starts

Quick start

1. Install the server

Plugin install is the shortest path.

Claude Code

bash
claude plugin marketplace add sunhome243/figma-mcp-expressclaude plugin install figma-mcp-express@figma-mcp-express

Codex

bash
codex plugin marketplace add sunhome243/figma-mcp-expresscodex plugin add figma-mcp-express@figma-mcp-express

2. Import the Figma Desktop plugin

  1. Download plugin.zip or build from source.
  2. In Figma Desktop, go to Plugins -> Development -> Import plugin from manifest....
  3. Select manifest.json from the unzipped plugin folder or from this repo's plugin/ directory.

3. Run it

  1. Open the target file in Figma Desktop.
  2. Start Plugins -> Development -> Figma MCP Express.
  3. Keep the plugin running while the agent works.
  4. If you open multiple files, each file gets its own channel ID for multi-file workflows.

Important limits

  • Most live tools require the target file to be open in Figma Desktop with the plugin running.
  • fetch_library_catalog is the main REST-only exception and requires FIGMA_TOKEN.
  • Plugin execution is still single-threaded per file; the server reduces contention, but it does not make one file fully parallel.
  • Community kits must be published as a library before import_component_by_key can use them.
  • Remote follower (beta) is private Tailnet-only. It is not a public MCP URL: keep the leader loopback-only, expose it with Tailscale Serve (never Funnel), and connect the AI client to the follower's local /mcp. See DEV-SETUP.md.
Build from source

For other MCP clients, or if you want to modify the server:

bash
git clone https://github.com/sunhome243/figma-mcp-express.gitcd figma-mcp-expressmake build

This produces bin/figma-mcp-express and plugin/dist/.

Add it to your .mcp.json:

json
{  "mcpServers": {    "figma-mcp-express": {      "command": "/absolute/path/to/bin/figma-mcp-express",      "args": ["--port", "1994"]    }  }}

Restart your MCP client after building.

Advanced environment variables

FIGMA_TOKEN

Most workflows do not need a token. Live read/write tools talk directly to Figma Desktop through the plugin.

You only need FIGMA_TOKEN for REST-backed library catalog lookups such as fetch_library_catalog.

  • Generate it in Figma at Account Settings -> Personal access tokens
  • Read-only file access is enough for catalog lookup
  • Treat it like a password and never commit it

If you installed from the marketplace, set it in your shell profile:

bash
echo 'export FIGMA_TOKEN=your_token_here' >> ~/.zshrcsource ~/.zshrc

If you built from source, you can either export it in your shell or place it in a local .env file:

bash
cat <<'EOF' > .envFIGMA_TOKEN=your_token_hereEOF

Shell environment variables take precedence over .env.

VariableDefaultDescription
FIGMA_TOKEN-Required only for fetch_library_catalog.
FIGMA_MCP_TOOL_PROFILEcorecore keeps the compact default tool surface. full restores the legacy compatibility/debugging surface.
FIGMA_MCP_TOOL_SCHEMA_MODEcompactcompact trims tools/list descriptions to reduce MCP context tokens. Use verbose for full in-schema guidance.
FIGMA_MCP_BATCH_MAX_OPS200Maximum top-level batch.ops entries accepted before plugin execution.
FIGMA_MCP_BATCH_MAX_BYTES2097152Maximum encoded batch.ops payload size in bytes before plugin execution.
FIGMA_MCP_STDIO_WORKERS16Number of stdio tool-call workers. Server-local tools can run concurrently; plugin-facing calls still serialize per Figma file.
FIGMA_MCP_STDIO_QUEUE1000Buffered stdio tool-call queue size before mcp-go falls back to synchronous handling.
FIGMA_MCP_SPILL_BYTES25000Response size threshold. Larger responses spill to .figma-mcp-cache/.
FIGMA_MCP_TIMEOUT120Inactivity ceiling in seconds for lightweight ops. Resets on each progress heartbeat.
FIGMA_MCP_READ_TIMEOUT600Inactivity ceiling in seconds for heavy reads and batch. Resets on each progress heartbeat.
FIGMA_MCP_STALL_THRESHOLD45Seconds an op may hold a channel's serial slot with no progress before a new call on that channel is fast-rejected.

More docs

Credits

The original bridge architecture and implementation underlying this project were created by GETHOPP LTD in gethopp/figma-mcp-bridge@82b28bc and released under the MIT License.

figma-mcp-express was initially created from an intermediate fork without knowing this earlier provenance. After learning the full lineage, we restored GETHOPP LTD's copyright notice and now credit the original project directly. We value a healthy, transparent open-source ecosystem and aim to make authorship and derivation explicit.

Required third-party copyright notices are preserved in LICENSE. figma-mcp-express is MIT-licensed and permits commercial use.

Source: README.md at commit dcc3a10

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v2.8.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Figma integrations

Figma MCP Server

com.figma.mcpOfficial publisher

Figma's remote MCP server that gives AI coding agents design context from Figma files so they can generate and update code.

Streamable HTTPWeb executableAuth
Developer ToolsCredential requiredOct 24, 2026

Figma Vector MCP

Published by GitHub account workingmodel

Local MCP server plus Figma plugin that lets an assistant create and edit fully editable vector nodes, shapes, text and components on the Figma canvas.

STDIODesktop only
Developer Tools58 toolsOct 30, 2026

Figma CodeKit MCP

Published by GitHub account Mehmoodqureshi

Converts a Figma frame into HTML, React or Next.js code and pixel-diffs the rendered result against the design until it converges.

STDIODesktop only
Developer Tools3 toolsNov 7, 2026

figma-mcp

Published by GitHub account Mehmoodqureshi

Converts a Figma frame into deterministic HTML, React or Next.js code, then renders it in Chromium and pixel-diffs it against the design until it matches.

STDIODesktop only
Developer ToolsNot validated yetOct 24, 2026

figma-vault

Published by GitHub account NBhey

A local MCP server that lets an assistant read Figma designs pulled once into a vault, offline and without a Figma token or rate limits.

STDIODesktop only
Knowledge & MemoryNot validated yetOct 25, 2026