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.
-
Local studio for comics, images and LoRA training (Windows/Linux, NVIDIA) - bundled ComfyUI, plugins, MCP server
NOASSERTION ★ 6 -
ComfyUI workflows and GPU LoRA training in Gemini CLI. AI image models FLUX 2 and Seedream 5.0; AI video models Seedance 2.5, Wan 3.0, Wan 2.2 and LTX 2.5.
MIT -
Self-hosted AI studio on your own GPU: chat with your files (RAG), screen and browser agents, coding swarms, LoRA training, an MCP server for Claude Code and Cursor, and local video, image, music and voice generation. No telemetry.
pypi MIT ★ 320 -
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 -
A local studio to tune and extend language models: versioned datasets, LoRA and QLoRA training on the allowed GPUs, merges, GGUF conversion, importance-matrix quantization, YaRN context extension and evaluation against the base model. MCP tools for assistants.
MIT -
dsh-unslothactive
Unsloth for DeepSeek Harness: local LLM fine-tuning and dataset generation. Bundles a zero-dependency Python MCP server and mounts DSH's own MCP client, exposing model inventory, Data Recipe dataset generation, LoRA/QLoRA training, GGUF export and inferen
npm MIT -
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 -
AI that trains AI: analyse your data and hardware, pick a method, train, tune and deploy models on your own machine — from a CLI, MCP, a web GUI or one sentence.
pypi MIT -
Train a writing model on your prose, then draft in your voice from the CLI or any MCP client.
pypi MIT -
Train a model to write the way you speak, on your Mac. Skill + MCP rewrite() for Claude Code and Codex.
-
pocketmodelactive
Pocket Model from your terminal and your agent: find the smallest model that does your task, train it on your data, and serve it. CLI and MCP server.
npm MIT -
Two Model Context Protocol (MCP) servers for self-hosted, local AI: manage and train Ollama/vLLM models, and route questions and tasks to local LLMs through Claude, ChatGPT or local models. Use the compute of your existing hardware, and let the models tap data on your machines when you wire them in.
pypi MIT