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. 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, workflow wrapper and web app for Hugging Face diffusers
pypi Apache-2.0 ★ 18 -
—
★ 1 -
diffusion-llm-mcpgithub.com/sandraschi/diffusion-llm-mcpupdated this year
FastMCP fleet MCP server for diffusion LMs (dLLM). DiffusionGemma on Goliath RTX 4090 — batch inference, HLE-shaped reasoning, ~200–400 tok/s. Doc phase; llama-diffusion-cli sidecar next. Complements local-llm-mcp.
MIT ★ 2 -
🎨 Enhanced Stable Diffusion MCP Server - Full-featured AI art generation with text-to-image, image-to-image, model switching, LoRA support, and prompt analysis
NOASSERTION -
FastMCP server for the Animagine XL 4.0 image generation experience, providing prompt validation, optimization, explanation, img2img, and checkpoint/LoRA management tools. Works for any Stable Diffusion XL based model.
MIT ★ 1 -
Generate and edit images from Claude Code on your own GPU. MCP server + CLI for local GGUF models (Z-Image, FLUX.2 klein) via stable-diffusion.cpp.
Apache-2.0 -
DiffusionGemma node pack for ComfyUI, built on MCP backbone for fully-agentic consumption — discrete diffusion text generation with per-step canvas snapshots, commit heatmaps, and structured trace data. Watch meaning crystallize out of noise.
GPL-3.0 ★ 1 -
gelbooru-mcpgithub.com/citronlegacy/gelbooru-mcpupdated this year
Generate stable diffusion prompts and explore character appearance and art data from Gelbooru via MCP.
MIT ★ 1 -
Local image generation and editing MCP server (Rust): Qwen-Image-2.1 via stable-diffusion.cpp, pluggable backends, MCP Tasks
NOASSERTION ★ 1 -
anime-sd-mcpgithub.com/haotongliu58-sudo/anime-sd-mcpupdated this year
An MCP server to generate anime images via a local Stable Diffusion XL backend
MIT ★ 1 -
mcp-sd-tts-servergithub.com/yyboling-commits/mcp-sd-tts-serverupdated this year
MCP Server for Stable Diffusion (txt2img) and TTS (GPT-SoVITS)
-
MCP server for Morphogen II: read and sign the guestbook of a living reaction-diffusion field with open questions for AI agents
npm MIT ★ 2 -
Offline text-to-image for your own GPU, exposed as an MCP server and a CLI. Bridges the stable-diffusion.cpp engine bundled with LocModel; no cloud, no API keys.这个程序可以将locmodel与智能体建立连接,在智能体中可以自动通过locmodel生成图片加入agent工作。向locmodel的开发者们致敬
MIT ★ 3 -
Robot learning stack for a real WidowX AI arm: demo capture, calibrated MuJoCo digital twin, Diffusion Policy with real-time chunking, π₀.₅/LeRobot in Docker, and LLM tool-calling control over MCP.
NOASSERTION -
MCP server that brings Stability AI to Claude Code — image generation, editing, upscaling, ControlNet, and 3D mesh generation. 15 tools powered by Stable Diffusion 3.5, Stable Image Ultra/Core, and Stable Fast 3D.
MIT -
mcp-image-gengithub.com/aitherlab-dev/mcp-image-genupdated this year
MCP server for local image generation via diffusion-rs (Stable Diffusion, FLUX). Works with Claude Code, Claude Desktop, and any MCP client.
MIT ★ 2 -
MCP server for Stable Diffusion WebUI Forge Neo — generate images on your own GPU from any MCP-capable agent. Reads the loaded checkpoint, infers sampling parameters and prompt style from your settings and past generations, and writes the prompt.
MIT ★ 1 -
MOSS-SoundEffect_v2.0_MPS_ROCmgithub.com/VladimirTalyzin/MOSS-SoundEffect_v2.0_MPS_ROCmupdated this year
Desktop app for the MOSS-SoundEffect-v2.0 text-to-audio diffusion model, with working AMD ROCm (Windows) and Apple Silicon (MPS) support. No API keys, no browser. Includes CLI, benchmark tools and an MCP server.
Apache-2.0 -
tarhangithub.com/emircbngl/tarhanupdated this year
Physics-first 0D/1D materials simulator, validation-first: pn-diode drift-diffusion, PEMFC/SOFC fuel cells and electrochemistry, each pinned to a source-cited reproduction test. Ships an MCP server exposing 9 guarded tools so AI agents can drive it. DEVSIM cross-check optional.
Apache-2.0 -
Bulk AI image generation on your own Windows PC: FLUX.2, Qwen-Image, SDXL and more via stable-diffusion.cpp. Batches, reference images, LoRAs, upscaling, an OpenAI-compatible API and an MCP server for AI agents. No cloud, no account.
MIT -
DiffuGen is a powerful yet user-friendly interface for local\edge image generation. Built on the Model Control Protocol (MCP), it provides a seamless way to interact with various Stable Diffusion models including Flux, SDXL, SD3, and SD1.5. Diffugen also features an OpenAPI Server for API usage and designed to support OpenWebUI OpenAPI Tool use.
MIT ★ 19 -
EDMCPgithub.com/AvidGameFan/EDMCPupdated this year
MCP Server for Easy Diffusion
★ 2 -
ncnn_llm-mcp-sdimggengithub.com/chentyjpm/ncnn_llm-mcp-sdimggenupdated this year
基于 ncnn 的 Stable Diffusion 推理小工具,用于给 ncnn-llm 适配“图片生成”能力(作为 MCP 工具/后端可执行程序被调用)。
★ 18 -
A thin MCP wrapper around a local Stable Diffusion WebUI (Forge Neo) instance
Apache-2.0 -
A MCP server that provides text-to-image generation capabilities using Stable Diffusion WebUI API (ForgeUI/AUTOMATIC-1111)
MIT ★ 44 -
Bedrock Image MCP-server for Nova Canvas and Stability Diffusion 3.5 Large and Stability AI tools. This project was originally based on the AWS Labs Nova Canvas MCP Server.
Apache-2.0 -
AiFP Cognitive Memory — persistent memory MCP server for AI assistants. Chinese-first retrieval with causal chains, Hebbian associations and graph diffusion. 记忆感知系统
npm SEE LICENSE IN LICENSE -
Professional TypeScript Model Context Protocol (MCP) server & agent skill for optical profiling, physical relighting, composite harmonization, and diffusion prompt synthesis (Any Image Generator Model / GEMINI Nano Banana).
npm MIT -
mcpgithub.com/promptibus/mcpupdated this year
Model intelligence MCP server — syntax, parameters, pricing for 67+ generative AI models (Midjourney, Flux, Suno, Runway, DALL-E, Stable Diffusion). 7 tools for any MCP client.
npm MIT ★ 3 -
Etch — deterministic vector sketching for AI agents. An MCP server that assembles editable SVG scenes from typed components with brand tokens enforced at render time. No diffusion, real fonts, surgical edits.
MIT ★ 1 -
Brain-like persistent memory for AI agents. Hybrid search, knowledge graph, sleep-consolidation lifecycle, expert routing (HMoE), and a graph-Laplacian diffusion subsystem driving decay, consolidation, auto-link, and spectral retrieval. 63 MCP tools. Local, no cloud.
nuget MIT ★ 7 -
Local AI desktop app: a Chromium browser with a GPU-aware llama.cpp runtime, OpenAI-compatible API, AI chat and agents, Stable Diffusion image/video, TTS and music, plus an MCP server so Claude Code, Codex and Cline can drive your browser. Windows, macOS, Linux.
NOASSERTION ★ 151 -
Preservation-aware visual dataset curation & contrastive safety alignment engine for AI. Replaces destructive whole-image sample-dropping and diffusion inpainting drift with deterministic sub-pixel Rust SDF masking, 540p JPEG survivability verification, and zero-glue MCP server for foundation VLM pre-training and DPO.
NOASSERTION ★ 1 -
MCP server for fal.ai image generation
npm MIT -
wpa-poster-sdxlgithub.com/nishankpt/wpa-poster-sdxlupdated this year
SDXL LoRA fine-tuned on public-domain WPA posters + a CLIP/FID/KID eval harness + MCP server. Trained and evaluated end-to-end on an 8GB laptop GPU.
MIT -
@pseem/server-koboldaistale
MCP server for KoboldAI API integration
npm MIT -
@mseep/server-koboldaistale
MCP server for KoboldAI API integration
npm MIT -
comfyui-mcpgithub.com/tabbykat113/comfyui-mcpupdated this year
MCP server that connects AI agents to a running ComfyUI instance for image generation
MIT ★ 1 -
rfdiffusion2_mcpgithub.com/MacromNex/rfdiffusion2_mcpupdated this year
RFdiffusion2 MCP server for protein structure generation (backbone)
★ 1 -
MCP server exposing NovelAI image generation as tools for AI agents
pypi MIT -
comfyui-agentgithub.com/josephoibrahim/comfyui-agentupdated this year
AI co-pilot for ComfyUI — inspect, discover, modify, and execute workflows through natural conversation
pypi MIT -
MCP server for a local Forge/A1111 SDXL backend — image generation as tools, built for a shared GPU.
MPL-2.0 -
Octop AI Agent 通过 MCP 协议直接驱动本地 ComfyUI 出图 / 出视频的集成方案(纯本地推理,零云端花费)
MIT -
Local studio for comics, images and LoRA training (Windows/Linux, NVIDIA) - bundled ComfyUI, plugins, MCP server
NOASSERTION ★ 6 -
mcp-drawthingsgithub.com/james-see/mcp-drawthingsupdated this year
MCP server for Draw Things - local AI image generation on Mac
npm MIT -
InvokeAI creative engine bridge - generate (txt2img/img2img/inpaint/upscale), queue, models, gallery, boards, workflows + SOTA webapp
MIT ★ 2 -
A Model Context Protocol server for browsing and discovering AI models on Civitai
MIT ★ 13 -
forge-mcpgithub.com/NixonMSilva/forge-mcpupdated this year
An MCP server to use with sd-webui-forge (and sd-webui-forge-neo) built for Claude Desktop / Cowork.
MIT ★ 1 -
hitomigithub.com/grimmjoww/hitomiupdated this year
Hitomi — creations become reality. Unified MCP for anime/therian illustration and voice generation via ComfyUI.
NOASSERTION -
Local MCP server bridging Claude Code to ComfyUI for FLUX-Krea / FLUX-Kontext on RTX 3080 Ti.
MIT -
肥鱼生图车道:一条已验证的动漫画风基线(SDXL + 4 LoRA 链)+ MCP 出图工具;模型与 LoRA 定位、可跑 ComfyUI 工作流、非 R18 提示词手册、示例图完整参数
NOASSERTION -
deepghs-mcpgithub.com/citronlegacy/deepghs-mcpupdated this year
MCP server for the DeepGHS anime AI ecosystem. Dataset discovery, tag search, character dataset finder, and training pipeline code generation.
MIT ★ 1 -
@iflow-mcp/artokun-comfyui-mcpgithub.com/artokun/comfyui-mcpupdated this year
MCP server for ComfyUI — workflow execution, visualization, composition, registry, and skill generation
npm MIT -
nft-pipeline-mcp-servergithub.com/MyronKoch/nft-pipeline-mcp-serverupdated this year
Chain-agnostic NFT creation pipeline: AI image generation → IPFS storage → metadata → mint-ready
MIT -
Agentic ComfyUI image generation over the Model Context Protocol: batch discovery, LoRA shaping, and provenance.
pypi MIT -
MCP server for the Tensor.Art TAMS API: generate images with your own LoRA from Claude, Cursor or any MCP client
MIT -
Local dashboard for ComfyUI: live progress, previews, queue, gallery and logs. Works with comfy-mcp. English/Spanish UI.
MIT -
@mindbreaker81/openrouter-imageupdated this year
MCP server and CLI for image generation/editing via OpenRouter's Responses API
npm MIT -
MCP server supporting multiple AI providers for image generation - OpenAI, Stability AI, Replicate, HuggingFace
npm ISC -
Comfy-Cozygithub.com/JosephOIbrahim/Comfy-Cozyupdated this year
AI copilot for ComfyUI. Say “dreamier” and the workflow shifts, instantly and reversibly.
pypi MIT ★ 24