LogoAIAny
Icon for item

Figma MCP Server

MCP server that streams structured Figma design data to coding agents like Cursor, enabling one-shot UI implementation from designs.

Visit Website
Visit Website

Introduction

Overview

Framelink’s Figma MCP Server exposes a Figma project’s full layer tree, constraints and style tokens through the Model Context Protocol so AI coding tools can translate designs directly into production-ready components.

Key Capabilities
  • Figma API sync – fetches frames, components, text styles and tokens on demand
  • Diff-aware snapshots – sends only changed nodes to minimise context size
  • Language-agnostic – agents can output any front-end framework or design system
  • Auth workflow – OAuth-based linking of multiple Figma files & workspaces
  • CLI & Docker images – quick local or cloud deployment for teams**
Back

Information

  • Websitegithub.com
  • AuthorsGLips
  • Published date2025/05/21

Categories

Tags

More Items

Icon for item

PAL MCP Server

2023
BeehiveInnovations

PAL MCP Server is an open-source Model Context Protocol (MCP) server developed by BeehiveInnovations. It enables integration of multiple AI models (e.g., Gemini, OpenAI, Anthropic, Grok, Ollama) into a unified context, supporting tools like Claude Code, Gemini CLI, and Codex CLI for collaborative workflows. It enhances code analysis, problem-solving, and development by allowing multi-model conversations with seamless context continuity, bypassing single-model limitations.

mcp-serverai-codingclaudegeminiopenai+4
Icon for item

MarkItDown

2024
Microsoft

MarkItDown is a lightweight Python utility for converting various files and office documents to Markdown, designed for use with large language models (LLMs) and text analysis pipelines. It preserves document structure like headings, lists, tables, and links, making it ideal for AI applications. Supports PDF, PowerPoint, Word, Excel, images (with OCR), audio (with transcription), HTML, text formats, ZIP, YouTube, and EPub.

ai-toolsmcpmcp-servermicrosoftllm
Icon for item

LEANN

2025
Yichuan Wang, Zhifei Li +1

LEANN is the world's smallest vector index, enabling RAG on everything from documents to chat histories with 97% storage savings, no accuracy loss, and 100% privacy on personal devices. It uses graph-based selective recomputation and high-degree preserving pruning for lightweight, scalable semantic search.

RAGgithubai-libraryai-toolsai-development+5