MCP servers for design & media

ahujasid/mcp-for-blender

↗

Community plugin to control Blender 3D with any LLM of your choice. Not affiliated with the official Blender Foundation.

No credential named

grab/cursor-talk-to-figma-mcp

↗

TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.

No credential named

loonghao/photoshop-python-api-mcp-server

↗

A Model Context Protocol (MCP) server that interfaces with Adobe Photoshop's Python API. Enables LLMs to execute image editing operations, automate workflows, and manage Photoshop tasks through structured commands and context-aware interactions.

No credential named

burningion/video-editing-mcp

↗

MCP Interface for Video Jungle

No credential named

hellokaton/unsplash-mcp-server

↗

🔎 A MCP server for Unsplash image search.

Needs UNSPLASH_ACCESS_KEY

KyaniteLabs/kinocut

↗

Guardrailed video editing MCP server for AI agents. FFmpeg, Hyperframes, repurposing tools, Python client, and CLI. Local, fast, free.

No credential named

MatthewDailey/figma-mcp

↗

ModelContextProtocol for Figma's REST API

Needs FIGMA_API_KEY

SupercmoHQ/superCMO-skills

↗

Open-source skills that empower any AI agent (Claude, Cursor, Hermes, etc.) to generate end-to-end marketing campaigns - UGC videos, ad videos, product photography and more.

Needs ELEVENLABS_API_KEY · FAL_KEY · FIRECRAWL_API_KEY · GEMINI_API_KEY · WAVESPEED_API_KEY

TimHolden/figma-mcp-server

↗

Model Context Protocol server implementation for Figma API

Needs FIGMA_ACCESS_TOKEN

tadasant/mcp-server-stability-ai

↗

MCP Server integrating MCP Clients with Stability AI-powered image manipulation functionalities: generate, edit, upscale, and more.

Needs STABILITY_AI_API_KEY

thirdstrandstudio/mcp-figma

↗

Figma MCP Server with full API functionality

Needs FIGMA_API_KEY

blacktop/mcp-tts

↗

MCP Server for Text to Speech

Needs ELEVENLABS_API_KEY · GOOGLE_AI_API_KEY · OPENAI_API_KEY

PatrykIti/blender-ai-mcp

↗

[Project discontinued] Production-shaped MCP server for Blender with goal-first routing, curated tools, deterministic verification, and vision-assisted 3D modeling workflows.

No credential named

attalla1/photopea-mcp-server

↗

MCP server for AI-driven image editing with Photopea

No credential named

themesberg/flowbite-mcp

↗

Convert Figma design to code with the official Flowbite MCP server

Needs FIGMA_ACCESS_TOKEN

barbosaihan/civil3d-mcp

↗

AI-Powered Civil 3D Modeling

No credential named

tercumantanumut/sunnysideFigma-Context-MCP

↗

A comprehensive Model Context Protocol (MCP) server that bridges Figma designs with AI development workflows. It provides 30 specialized tools for extracting pixel-perfect code, assets, and component structures directly from Figma designs.

Needs FIGMA_API_KEY

devizor/macOS-Notification-MCP

↗

macOS Notification MCP enables AI assistants to trigger native macOS sounds, visual notifications, and text-to-speech. Built for Claude and other AI models using the Model Context Protocol.

No credential named

loudreader/loudkit

↗

Local text-to-speech: 28 voices, 10 languages, voice cloning, SDKs for Python, Swift, Go, Rust and TypeScript

No credential named

kdoronin/figma_mcp

↗

Figma MCP server for accelerating layout development

No credential named

tahooki/unreal-blender-mcp

↗

unreal-blender-mcp

No credential named

bmorphism/say-mcp-server

↗

MCP server for macOS text-to-speech functionality

No credential named

Nam0101/android-mcp-toolkit

↗

A growing collection of MCP tools for Android Development. Currently features a deterministic Figma-SVG-to-Android-XML converter, with plans for Gradle analysis, Resource management, and ADB integration tools.

No credential named

miapre/mimic-ai

↗

The design system copilot that builds Figma from HTML using your real components and tokens. Learns your system, surfaces your gaps.

No credential named

Gorav22/Blender-mcp

↗

BlenderMCP connects Blender to Claude AI and cursor through the Model Context Protocol (MCP), allowing Claude and cursor to directly interact with and control Blender. This integration enables prompt assisted 3D modeling, scene creation, and manipulation.

No credential named

yubraaj11/ffmpeg-mcp

↗

A Python package for media processing using FFmpeg and FastMCP.

No credential named

douglarek/unsplash-mcp-server

↗

🔎 A MCP server for Unsplash image search.

Needs UNSPLASH_ACCESS_KEY

planetabhi/figma-mcp-server

↗

A local Figma MCP server with full Figma REST API coverage

Needs FIGMA_API_KEY

cloudinary/mcp-servers

↗

Official Cloudinary MCP Servers

Needs CLOUDINARY_API_KEY · CLOUDINARY_API_SECRET

felores/cloudinary-mcp-server

↗

MCP (Model Context Protocol) server for uploading media to Cloudinary using Claude Desktop

Needs CLOUDINARY_API_KEY · CLOUDINARY_API_SECRET

kshern/image-tools-mcp

↗

A Model Context Protocol (MCP) service for retrieving image dimensions, supporting both URL and local file sources.

Needs FIGMA_API_TOKEN · TINIFY_API_KEY

shinshin86/mcp-simple-aivisspeech

↗

A Model Context Protocol (MCP) server for seamless integration with AivisSpeech text-to-speech engine. This project enables AI assistants and applications to convert text to natural-sounding Japanese speech with customizable voice parameters.

No credential named

JavaProgrammerLB/unsplash-mcp-server

↗

java version unsplash mcp server

Needs UNSPLASH_ACCESS_KEY

199-mcp/mcp-elevenlabs

↗

Fork of ElevenLabs MCP server with enhanced conversational AI features

Needs ELEVENLABS_API_KEY

ArchimedesCrypto/figma-mcp-chunked

↗

Use Figma in a MCP with Chunking Support

Needs FIGMA_ACCESS_TOKEN

xlzuvekas/figma-copilot

↗

MCP & Plugin connectors for UPDATING and CREATING Figma designs. Unofficial integration.

No credential named

sensormcp/sensor-mcp

↗

MCP server that lets an LLM build a custom object detector by chat: fetch images, auto-label with GroundedSAM, train YOLOv8.

Needs UNSPLASH_API_KEY

arturskowronski/reachy-mini-mcp

↗

MCP server that lets AI assistants control the Reachy Mini robot. Connect Claude, ChatGPT, or any MCP-compatible client and control head movement, antennas, emotions, camera and audio through natural language.

Needs ELEVENLABS_API_KEY · REACHY_ELEVENLABS_API_KEY

vipulawl/mcp-changeimageto

↗

Image editing MCP for Cursor & Claude: remove background, blur BG, upscale, OCR, PDF, Gemini text edits, inpainting, bulk tools. Model Context Protocol.

No credential named

LucasGorgal/localfig

↗

The Figma desktop app as an MCP server. Gives AI agents the full Figma Plugin API on your open file: read, write, tokens, components, exports, undo. Runs locally with no cloud API, no token and no quota. One command registers it with Claude Code, Cursor, VS Code, Windsurf, Cline, Gemini CLI, Codex and more. Zero dependencies.

No credential named

kolganovr/figma-mcp-bridge

↗

Let an AI agent design in Figma - and actually see what it drew. Zero-dependency MCP bridge with write access, screenshots, and undo.

No credential named

vizionik25/moviepy-mcp

↗

Self Contained Video Editing Agent using FastAPI, FastMCP, MoviePy v2.2.x, OpenCV, Next.js/React, Typescript, Tailwind CSS

No credential named

hanoak/unsplash-mcp-server

↗

Production-ready Model Context Protocol (MCP) server for the Unsplash API — search & fetch photos, collections, topics, users, and stats, with built-in attribution and download-tracking compliance. For Claude, Cursor, and any MCP client. Unofficial.

Needs UNSPLASH_ACCESS_KEY

adminmetavision-rgb/metavision-mcp

↗

MetaVision MCP Server - AI 3D model generation for Claude Desktop and AI assistants

No credential named

MuhammadTayyabIlyas/CHeema-Text-to-Voice-MCP-Server

↗

Free, local text-to-speech and voice cloning MCP server for Claude Desktop, Claude Code, and n8n. No API keys, no cloud, no per-character billing.

No credential named

nakai95/ui-prototype

↗

Modern React + TypeScript + Material-UI web application with authentication, internationalization, testing, and Figma MCP integration

No credential named

engr-faizanali/text-to-speech-mcp

↗

Local text-to-speech MCP server for Windows, macOS, and Linux. No API key, no account, no cloud.

No credential named

rocnubie/wordcast-mcp

↗

WordCast is a browser-based text-to-speech reader that converts written content into audio entirely on your device. There is no backend server involved: text, files, and URLs are processed locally using the speech synthesis voices already installed on your operating system.

No credential named

boraalapgh/figma-vue-design-system

↗

Production-ready Vue 3 design system components generated from Figma using MCP, documented in Storybook

No credential named

cristinafores/design-context-bridge

↗

Client-agnostic MCP server that exposes live Figma design context to any AI agent supporting the Model Context Protocol

No credential named

fasuizu-br/brainiall-tts-mcp

↗

Hosted pay-per-use text-to-speech MCP server — 54 neural voices, 9 languages incl. Brazilian Portuguese. $0.008/1K chars, $10 free credits.

Needs APIM_KEY

rocnubie/nanobanana-mcp

↗

Nano Banana Pro AI is an online image and video editing platform that uses multiple AI models to handle visual tasks that would otherwise require dedicated design software or manual effort.

No credential named

arrow2nd/vv-mcp

↗

🤖 VOICEVOX MCP Server for text-to-speech synthesis with Claude

No credential named

Gandr-AI/gandr-mcp

↗

The official Gandr MCP server, text to speech inside any MCP-compatible agent

Needs GANDR_API_KEY

ropon/MiniMax-MCP

↗

Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech and video generation APIs.

Needs MINIMAX_API_KEY

leo9iota/tts-mcp

↗

Text-to-Speech MCP Server for IDEs

Needs ELEVENLABS_API_KEY · FISHAUDIO_API_KEY