What makes Figma Mcp Express different from other Figma MCP servers?
It uses a local plugin bridge, so no Figma token, quota, or per‑seat billing is required, and it offers 70 tools covering reading, creating, mutating, importing, and exporting.
@sunhome243
基本信息
figma-mcp-express connects AI agents directly to Figma via a local plugin bridge. No Figma token required. No quota. No per-seat billing. Ships 70 discrete tools for reading design context, creating and mutating nodes, importing library components and variables, managing styles a
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"figma-mcp-express": {
"command": "npx",
"args": [
"-y",
"figma-mcp-express"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
Figma Mcp Express connects AI agents directly to Figma via a local plugin bridge. It requires no Figma token, no quota, and no per‑seat billing, and is designed for agent‑driven design automation in MCP‑compatible clients like Claude, Cursor, and Codex.
Install the MCP server and the companion Figma plugin, then configure your MCP client to point to the server. Specific invocation commands or config keys are not detailed in the README.
It uses a local plugin bridge, so no Figma token, quota, or per‑seat billing is required, and it offers 70 tools covering reading, creating, mutating, importing, and exporting.
You need a Figma plugin installed alongside the MCP server; the README does not specify further runtime requirements.
Data stays within your local Figma session and the plugin bridge; no external API is called.
The README does not describe specific transports or auth mechanisms beyond the local plugin bridge.
No limits are mentioned in the README beyond the absence of quota or billing.

Routebase keeps your API's design, docs, contract tests, mocks and monitoring in one living OpenAPI spec so they can't drift apart. Agents work on that same source of truth, under your team's permissions.

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U
评论