mcpField
L
Layerbridge

Layerbridge

Local
github.comMedia & Design1Updated 6w ago
RepositoryVisit website

About Layerbridge

Read, edit, and export the Figma file open in a local plugin. No REST API, no rate limits

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "muradyf-layerbridge": {
      "command": "npx",
      "args": [
        "-y",
        "layerbridge"
      ],
      "env": {
        "FIGMA_BRIDGE_PORT": "<FIGMA_BRIDGE_PORT>",
        "FIGMA_BRIDGE_OUTPUT_ROOTS": "<FIGMA_BRIDGE_OUTPUT_ROOTS>",
        "FIGMA_ACCESS_TOKEN": "<FIGMA_ACCESS_TOKEN>",
        "FIGMA_BRIDGE_ALLOW_SCRIPTS": "<FIGMA_BRIDGE_ALLOW_SCRIPTS>"
      }
    }
  }
}
Run commandnpx -y layerbridge
Environment variables to set
FIGMA_BRIDGE_PORTLocal port the Figma plugin connects to; choose the same port in the plugin panel
FIGMA_BRIDGE_OUTPUT_ROOTSExtra folders export tools may write to (; on Windows, : elsewhere). Default: working directory only
FIGMA_ACCESS_TOKENSecretOptional Figma personal access token; enables REST tools (comments, versions, team files)
FIGMA_BRIDGE_ALLOW_SCRIPTSAllow the run_script tool to execute Plugin API code in the open file

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmlayerbridge0.3.0

Tools

116

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
pageIdstringNoOnly this page (faster on big files)
fileKeystringNoThe fileKey of the Figma file. Required when several files are connected; see list_files.
includeVariantsbooleanNoAlso list each variant inside a set (default false)

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.