figmanage MCP Server
io.github.dannykeane/figmanage
Manage Figma workspaces with 102 tools for files, teams, seats, and offboarding via AI agent or CLI.
What is the figmanage MCP server?
Figmanage is an MCP server that lets AI agents and users manage Figma workspaces programmatically. It provides 102 tools for finding files, organizing projects, reviewing access, managing teams and seats, and handling offboarding tasks. Connect it to Claude, Cursor, or other MCP clients, or use it as a standalone CLI tool.
Figmanage automates Figma workspace administration. Find and organize files, audit team access, manage paid seats, and handle employee offboarding—all through natural language requests to your AI agent or direct CLI commands. It respects your Figma permissions and supports dry-run checks before making changes.
How to install figmanage
Copy-paste configuration for popular MCP clients.
Tools & capabilities
Tools this server exposes to the agent.
list-recent-files— Find files you worked on recentlymove-files— Move files into projectsshow-project-access— Review who has access to projectsfind-inactive-seats— Identify paid seats inactive for a specified periodoffboarding-review— Check what needs handing over before a team member leaveslist-teams— Show teams in your workspaceschema— Retrieve tool schema for agents and scriptsnavigate— Execute navigation and query commandslogin— Authenticate with Figma and manage credentials
Use cases
- Find and organize design files by project or date
- Audit team access and permissions across projects
- Identify and manage inactive paid seats to optimize costs
- Prepare offboarding checklists and transfer file ownership
- Automate workspace cleanup and file archival tasks
figmanage MCP server FAQ
Figmanage is an MCP server with 102 tools for managing Figma workspaces. You can ask your AI agent to find files, move them, review access, manage teams and seats, and handle offboarding—or use it as a CLI tool directly.
Yes, Figmanage is open-source (MIT license) and free to use. You need a Figma account and Node.js 18+.
Run `claude mcp add --transport stdio --scope user figmanage -- npx -y figmanage --mcp` in Claude Code, or generate a client config for Cursor, VS Code, or Claude Desktop via the setup docs.
Sign in to Figma in Chrome; Figmanage reads your session. For advanced features like comments and exports, add a Figma Personal Access Token via `npx -y figmanage login --pat-only`.
Yes. Use Figmanage for workspace management (files, access, teams, seats) and the official Figma MCP for design work. Your agent can pass file links between them.
Yes. Use `--dry-run` to check inputs without sending requests, and `--progress --jsonl` for offboarding workflows to monitor progress before execution.
README (reference)
Source of truth, from the repository.
figmanage
Manage your Figma workspace with your agent or terminal.
Find files, organize projects, review access, and manage teams and seats. Connect Figmanage to your AI assistant through MCP, or use the command-line tool yourself.
Try asking
- “Find the files I worked on this week.”
- “Move these files into the Archive project.”
- “Show who has access to this project.”
- “Which paid seats have been inactive for 30 days?”
- “Check what needs handing over before Jordan leaves.”
Figmanage uses your Figma permissions. Admin tasks need admin access.
Get started with your agent
You need Node.js 18+ and an agent that supports local MCP servers.
1. Add Figmanage. In Claude Code, run:
claude mcp add --transport stdio --scope user figmanage -- npx -y figmanage --mcp
Using Codex, Cursor, VS Code, or Claude Desktop? Generate your client config.
2. Sign in to Figma in Chrome, then ask your agent:
Set up Figmanage, then show my teams and recent files.
Your agent asks before reading your Chrome session. macOS may show a Keychain prompt. Your login is saved locally.
3. Give it a task. Start with one of the examples above.
Some features, such as comments and exports, also need a Figma Personal Access Token. Add it locally with npx -y figmanage login --pat-only, then reconnect MCP. Keep tokens out of chat. See account setup.
Use the terminal
npm install -g figmanage
figmanage login
figmanage navigate list-recent-files
Use figmanage --help to find commands, or figmanage doctor if setup needs attention.
For agents and scripts
Use MCP for tool discovery, or the CLI for automation:
figmanage schema
figmanage navigate list-recent-files --jsonl --no-input
- Readable by humans: terminal output stays easy to scan.
- Readable by scripts: choose
--jsonor--jsonl. With JSONL, require the final summary and check the exit code. - Check before changing:
--dry-runchecks inputs without sending requests. It does not check live permissions. - Follow progress: offboarding supports
--progress --jsonland MCP progress notifications when requested.
See the automation guide for output formats and the optional agent skill for workflow recipes.
Already use the official Figma MCP?
Use Figmanage to manage files, access, teams, and seats. Use the official Figma MCP for design work. Your agent can pass file links between them; each server has its own login. How they work together.
More help
- Setup and troubleshooting
- Commands and all 102 operations
- Offboarding and its limits — review the audit first. Execution can remove access, change file owners, and downgrade seats.
- Contribute · Changelog · MIT license
Related MCP servers
Analytics your AI agent can actually use. Track, experiment, and optimize via MCP.
View repository →
io.github.danpeig/plutocalcdesigner-mcp
Plutocalc Designer is a software suite for water and wastewater treatment plants design
MCP server for Yoto: manage cards, tracks, icons and family devices from any MCP client.
Search, read, cite, create, and safely update a user's private KeepFlash knowledge library.
Project Parva
Read-only Nepali date, calendar, festival, Panchanga, and temporal verification tools for agents and APIs.
Danube AI
Unified platform for AI tool discovery, execution, and integration across APIs and MCP servers.