Unlimited Figma MCP for AI agents via an open-source plugin
figma-console-mcp lets AI agents use Figma's Plugin API as an MCP server, bypassing the 20-call monthly limit on Figma's free tier.
The official Figma MCP has a limit of just 20 MCP calls per month on the free tier. A workaround appeared on GitHub: figma-console-mcp, an open-source plugin that exposes Figma's Plugin API to agents as a real MCP server.
The key point is that Figma's Plugin API has no call limits, while the plugin can still be reached through MCP.
Through it, an agent gets nearly the same functionality as the official MCP:
- create and edit frames, shapes, text, and more;
- configure prototype transitions;
- watch your edits in real time;
- and use 130 additional tools.
The only noticeable missing feature is Code Connect, which links components to code.
Setup:
- Download the desktop version of Figma.
- Give your agent the repository.
- It will create the Desktop Bridge plugin.
- Open the desired project.
- Enable the plugin: Plugins → Development → Figma Desktop Bridge.
It works on macOS and Windows.
Why it matters
AnalysisThis removes a practical cost barrier for agent-driven design workflows and shows how MCP can bridge existing plugin APIs.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Loop Engineering: Architecture of Autonomous Agentic Loops and the Post-Prompting Era
A deep dive into Loop Engineering: self-sustaining execution loops for Claude Code and autonomous agents, the DOER/CHECKER topology, deterministic verification, the /goal primitive, and reward hacking mitigation.
Building a Design System in Figma with Claude Code
Step-by-step guide to building a complete Figma design system using Claude Code: tokens, components, variables, and responsive screens.
Short-Term and Long-Term Memory of Agents
The architecture of multi-tier memory for autonomous agents. It distinguishes between Short-Term Memory (active context window of the current session) and Long-Term Memory (vector databases, user profile files, and episodic diaries).
A terminal sandbox for AI agents: terminal-mac for macOS
The open-source terminal-mac utility lets AI agents run a virtual macOS directly from the CLI, keeping them isolated from your main machine.