MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP server for the three.ws stack: free text-to-3D (TRELLIS) plus paid 3D, avatar, rigging and agent tools over x402.
Apache-2.0 ★ 9 -
Model Context Protocol(MCP) for TRELLIS(SOTA text-to-3d/image-to-3d) models
★ 11 -
trellis_blendergithub.com/FishWoWater/trellis_blenderupdated this year
Blender plugin for TRELLIS and TRELLIS.2 (3D AIGC Model, Text-to-3D, Image-to-3D)
★ 79 -
mymeshygithub.com/felippeomgt/mymeshyupdated this year
Local-first AI 3D asset generator - text/image to 3D, mesh texturing, PBR baking, multi-format export, and an MCP server for coding agents. Runs 100% on your own GPU.
MIT ★ 15 -
Unofficial MCP server for the Tripo 3D API (v3): text/image/multiview to 3D, P1/P2 low-poly, texturing, retopology, Smart UV, segmentation, rigging, animation, format conversion, Gaussian splats. Go, stdio, Claude Code plugin.
oci Apache-2.0 ★ 5 -
Text-to-CAD and AI 3D modeling for 3D printing. Create editable parametric models with GitHub Copilot or Claude Code, then preview and export 3MF/GLB.
Apache-2.0 ★ 4 -
local-asset-gen-mcpgithub.com/davidemodolo/local-asset-gen-mcpupdated this year
Local AI asset generation MCP server: end-to-end text-to-image/audio/speech and image/text-to-3D with Qwen3-TTS, Stable Audio Open, SSD-1B, and TripoSR.
GPL-3.0 ★ 3 -
meshy-mcpgithub.com/zyadhajaji/meshy-mcpupdated this year
MCP server for AI-powered 3D model & environment generation via Meshy AI — text to 3D, image to 3D, textures, GLB/FBX/USDZ — plug into Claude Desktop in 60 seconds
MIT ★ 3 -
3d-agent-mcpgithub.com/teslaproduuction/3d-agent-mcpupdated this year
AI-powered text-to-3D model generation agent with MCP server support. Local models (Hunyuan3D, TripoSR, FLUX) + cloud APIs.
MIT ★ 1 -
Self-hosted AI media studio on a Google Colab L4 GPU: text-to-image, image editing, text-to-video with sound, music, text-to-speech, voice cloning, image-to-3D and Whisper transcription. ComfyUI + web UI + MCP server.
AGPL-3.0 ★ 2 -
MCP server for Thrixel - text/image to editable, game-ready 3D assets.
pypi MIT -
MCP server that generates 3D models (text or reference image to GLB) using a Tripo Studio subscription — unofficial internal API
MIT ★ 2 -
MCP server for text-to-speech, speech-to-text, ARKit lipsync tracks and motion-capture clips for 3D agents.
Apache-2.0 ★ 10 -
MCP server for creating 3D objects with Babylon.js using text commands. Allows AI assistants like Claude to create and manipulate 3D objects through natural language.
MIT ★ 2 -
3D model creation for AI agents — MCP server + agent skill: 6 geometry engines (procedural, image, OpenSCAD, Blender, CadQuery, hosted), 15 equation-defined shape families, a procedural planet generator, profile-based validation, and a single-file Three.js viewer. Text-to-3D providers: Meshy, Tripo, Rodin.
NOASSERTION ★ 3 -
Agent-drivable bridge for NVIDIA ARDY: direct real-time text-to-motion humanoid animation via MCP. Toward an interactive prompting engine for real-time 3D.
AGPL-3.0 ★ 11 -
Text-to-3D city buildings MCP server & tools: NL -> CGA rules -> cloud engine -> glTF/glb
oci MIT -
asset-mcpgithub.com/OnePersonLabs/asset-mcpupdated this year
2D, 3D, audio asset generation for AI dev tools / agentic workflows - Fully textured text to 3D meshes, rigging, animations, images, SVG, sound effects, music, designed to support any backend - Meshy API (paid 3D asset gen service) or self-hosted setups you can easily set up with ComfyUI. Minimum config, without nerfing unique provider capabilities
MIT -
This is the code used to integrate a local LLM with Blender for generating 3D models using text prompts.
★ 1 -
AI game asset pipeline for Unreal Engine 5: text-to-3D (Meshy), text-to-motion (NVIDIA Kimodo), motion matching & blend spaces, AI sound (ElevenLabs), ComfyUI textures, Blender automation, MCP server.
AGPL-3.0 ★ 4 -
Local text-to-animation studio and MCP server for NVIDIA Kimodo. Plan natural-language or timed actions, generate and revise motion, inspect a textured 3D preview, compare candidates, reuse poses, and move verified exports through Blender and Unreal Engine. Works with Codex, Claude, and other MCP clients.
MIT ★ 1 -
atlascloud-mcpactive
MCP server for AI image / video / 3D / audio (TTS, music, speech-to-text) generation & LLM chat. Use Sora 2, Veo 3, Kling 3, Seedance 2, Flux 2, Nano Banana Pro, Hunyuan 3D, Seed Audio, Suno in Claude Code, Cursor, Codex, Gemini CLI.
npm MIT -
An MCP server implementation that integrates with 4o-image API, enabling LLMs and other AI systems to generate and edit images through a standardized protocol. Create high-quality art, 3D characters, and custom images using simple text prompts.
npm MIT ★ 4 -
Hand files from an AI coding agent's machine to your browser, and get told when you looked at them. Gallery shares with previews (images, video, audio, text, 3D models), zip downloads, forms and raw static sites; REST API + MCP server; callbacks into the agent's opencode session.
AGPL-3.0 ★ 1 -
mcp-server-3daistudiogithub.com/whale-professor/3daistudio_skillupdated this year
MCP server for 3D AI Studio — generate 3D models from text or images using Hunyuan and TRELLIS
pypi MIT -
MCP server for Meshy AI 3D generation platform
npm MIT ★ 93 -
modelforge-mcpactive
Local stdio MCP server for ModelForge: generate 3D models (GLB) from text or images and save them into a folder on your machine.
npm MIT -
MCP server that composes a placed 3D diorama plan from one sentence and browses saved scenes.
NOASSERTION ★ 10 -
Small MCP server for the Tripo 3D generation API
MIT -
MCP server for Hydrilla: generate 3D models and send them into Blender, Unity, Unreal, Godot, Maya or 3ds Max, and control 3ds Max scenes.
npm UNLICENSED -
PicoBerry MCP server — an AI 3D workspace for games, VR, and beyond. Generate, remesh, texture, and animate 3D assets from any MCP client. Multi-engine, one API.
npm MIT ★ 2 -
MCP server for FormFromLight - generate, rig, animate, build walkable worlds from kits and export 3D assets from Claude, Cursor and other MCP clients.
npm MIT -
pixibox-mcp-servergithub.com/aerovfx/pixi-mcp-serverupdated this year
Model Context Protocol server for Pixibox.ai — generate 3D models, control DCC tools (Blender/Houdini/Maya/UE5), manage assets, and orchestrate production pipelines via AI agents.
npm MIT -
Portfolio-safe Blender MCP execution core with isolated workers, reproducible 3D examples and a staged chat demo roadmap.
MIT -
Generate 3D models (GLB, USDZ) from YAML with a CLI or an MCP server for AI agents, or in the browser playground: a 3D editor you can also drive from your own AI chat.
npm MIT -
Build interactive 3D worlds with high-quality assets from Thrixel and your AI agent of choice.
Apache-2.0 ★ 116 -
Local CAD you can talk to: parametric B-Rep modeller, text-to-CAD, engineering drawings, print checks and an MCP server.
MIT -
Scenario for Unity: every Scenario model in the Unity Editor. Generate images, video, 3D, motion, audio, PBR materials and skyboxes; retexture, edit, remesh, rig, animate and split 3D models; priced before you spend; driven by people or by AI agents through a local MCP server.
MIT -
LiveAvatarStream3Dgithub.com/tech-sumit/LiveAvatarStream3Dupdated this year
🎬 Browser-based 3D talking-avatar studio — write a script, a lip-synced 3D presenter delivers it, export MP4 client-side with WebCodecs. Direction as data. Agent-native via WebMCP. No render server.
MIT ★ 2 -
Local-first multimodal CAD agent: photos, sketches & text in — verified, parametric, manufacturing-ready 3D models out (build123d, voxel FEM, topology optimization, MCP). Self-hosted, AGPLv3.
AGPL-3.0 ★ 2 -
CAD/CAE Copilot — an AI-native CAD/CAE/CAX workbench for AI agents. Text-to-CAD, text-to-CAE, real build123d/OpenCASCADE geometry, editable parameters, stable topology pointers, deterministic critique, and MCP server tools.
MIT ★ 94 -
Free, open-source AI builder for Minecraft: type a prompt or paste a picture and AI (Claude or Gemini) designs and builds it on your server. Text to build, image to statue, pixel art, and an MCP server. No mods needed.
MIT ★ 2 -
Give your AI agent an animated face. Describe a mascot, get a web component with idle, thinking, talking and error states. Blob and 3D styles are free; video uses your own fal key. CLI and MCP server for agents.
MIT ★ 3