mcp-figma
The mcp-figma server provides a Model Context Protocol interface to integrate with the Figma API for managing design resources.
Key capabilities:
API key management: Set, store, and verify Figma personal access tokens
File operations: Retrieve Figma files, specific nodes, and generate images from files
Comment management: Get, post, and delete comments on Figma files
Team and project access: Fetch projects for teams and files within projects
Component and style operations: Access components, component sets, and styles at team or file level
Image resources: Get URLs for images used as fills in Figma files
Provides comprehensive access to Figma's API, enabling file operations, comments management, team/project management, component and style access, and image extraction from Figma designs.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-figma get the file with key abc123"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-figma
A Model Context Protocol (MCP) server for Figma API integration, designed to be used with Claude and other MCP-compatible AI assistants.
Features
This MCP server provides access to Figma API functionality:
File operations (get file, get nodes, get images)
Comments management
Team/project management
Components and styles access
Persistent API key storage
Related MCP server: Figma MCP Server
Installation
NPM Installation
# Install globally
npm install -g mcp-figma
# Or install locally in a project
npm install mcp-figma
# Update to latest version
npm update -g mcp-figmaUsage with Claude
Add mcp-figma to your Claude configuration:
"mcp-figma": {
"command": "npx",
"args": [
"-y",
"mcp-figma"
]
}When using Claude, the first time you'll need to set your Figma API key:
Please use mcp-figma to set my Figma API key: figd_xxxxxxxxxxxxxxxxxxxxxxxYour API key will be stored in ~/.mcp-figma/config.json and will be automatically loaded in future sessions.
You can verify your API key is configured:
Please use mcp-figma to check my API key statusThen use any of the available Figma API functions:
Please use mcp-figma to get the file with key abc123Available Tools
The server provides the following tools:
set_api_key: Set your Figma API personal access token (saved to config)check_api_key: Check if an API key is already configuredget_file: Get a Figma file by keyget_file_nodes: Get specific nodes from a Figma fileget_image: Get images for nodes in a Figma fileget_image_fills: Get URLs for images used in a Figma fileget_comments: Get comments on a Figma filepost_comment: Post a comment on a Figma filedelete_comment: Delete a comment from a Figma fileget_team_projects: Get projects for a teamget_project_files: Get files for a projectget_team_components: Get components for a teamget_file_components: Get components from a fileget_component: Get a component by keyget_team_component_sets: Get component sets for a teamget_team_styles: Get styles for a teamget_file_styles: Get styles from a fileget_style: Get a style by key
For detailed usage examples, see USAGE.md.
License
MIT
Available Tools
18 toolscheck_api_keyA
Check if a Figma API key is already configured
Inputs: no named parameters.
delete_commentC
Delete a comment from a Figma file
Inputs: fileKey (required), comment_id (required).
get_commentsC
Get comments on a Figma file
Inputs: fileKey (required).
get_componentC
Get a component by key
Inputs: key (required).
get_fileC
Get a Figma file by key
Inputs: fileKey (required), version, depth, branch_data.
get_file_componentsC
Get components from a file
Inputs: fileKey (required).
get_file_nodesC
Get specific nodes from a Figma file
Inputs: fileKey (required), node_ids (required), depth, version.
get_file_stylesC
Get styles from a file
Inputs: fileKey (required).
get_imageC
Get images for nodes in a Figma file
Inputs: fileKey (required), ids (required), scale, format, +3 more.
get_image_fillsC
Get URLs for images used in a Figma file
Inputs: fileKey (required).
get_project_filesC
Get files for a project
Inputs: project_id (required), page_size, cursor, branch_data.
get_styleC
Get a style by key
Inputs: key (required).
get_team_componentsC
Get components for a team
Inputs: team_id (required), page_size, cursor.
get_team_component_setsC
Get component sets for a team
Inputs: team_id (required), page_size, cursor.
get_team_projectsC
Get projects for a team
Inputs: team_id (required), page_size, cursor.
get_team_stylesC
Get styles for a team
Inputs: team_id (required), page_size, cursor.
post_commentC
Post a comment on a Figma file
Inputs: fileKey (required), message (required), client_meta, comment_id.
set_api_keyA
Set your Figma API personal access token (will be saved to ~/.mcp-figma/config.json)
Inputs: api_key (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 18 tools
Most tools have distinct purposes targeting specific Figma resources like files, comments, components, styles, and images. However, get_file_nodes and get_image_fills could potentially overlap in purpose since both deal with retrieving node-related data, though their descriptions clarify different focuses (nodes vs. image fills).
All tool names follow a consistent verb_noun pattern using snake_case, with clear actions like get, post, delete, set, and check. This uniformity makes the toolset predictable and easy for an agent to navigate without confusion.
With 18 tools, the count is slightly high but reasonable for a Figma API server that needs to cover multiple resource types (files, comments, components, styles, images, projects, teams). It avoids being overwhelming while providing comprehensive functionality, though it could be trimmed slightly for tighter scoping.
The toolset offers complete coverage for core Figma operations, including CRUD for comments (get, post, delete), retrieval for files, components, styles, images, projects, and teams, and configuration for API keys. There are no obvious gaps, and agents can perform typical workflows without dead ends.
Related MCP Connectors
The Figma MCP server brings Figma design context directly into your AI workflow.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
The Telnyx MCP server is an official implementation of the Model Context Protocol that enables AI clients (like Claude Desktop, Cursor, and OpenAI Agents) to interact with Telnyx's telephony, messaging, and AI assistant APIs. It provides comprehensive capabilities including making and managing phone calls, sending SMS/MMS messages, purchasing and configuring phone numbers, creating AI assistants with custom instructions, managing cloud storage buckets, scraping and embedding website content, and handling integration secrets. The server exists as both a local implementation and a remotely hosted version, allowing developers to integrate real-world communication infrastructure directly into AI applications.
Related MCP Servers
- FlicenseBqualityDmaintenanceEnables AI assistants to interact with Figma files through the ModelContextProtocol, allowing viewing, commenting, and analyzing Figma designs directly in chat interfaces.52,780 npm214-
- FlicenseBqualityDmaintenanceA Model Context Protocol server that integrates with Figma's API, allowing interaction with Figma files, comments, components, projects, and webhook management.52,780 npm-
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that integrates Figma design files with AI coding tools like Cursor, Windsurf, and Cline, allowing AI tools to access and understand Figma design data for generating more accurate code.365 npm30MIT
- AlicenseAqualityDmaintenanceA Model Context Protocol server for interacting with the Figma API that handles large Figma files efficiently through memory-aware chunking and pagination capabilities.713 npm5MIT