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-automlgithub.com/idea7766/mcp-automlupdated this year
—
MIT ★ 1 -
—
-
AutoML MCP Server - Complete ML workflow automation with web interface
★ 1 -
automl-stat-mcpgithub.com/u9401066/automl-stat-mcpupdated this year
AI-powered statistical analysis and AutoML platform using Model Context Protocol (MCP)
Apache-2.0 ★ 3 -
AutoML_for_RAG-publicgithub.com/Zyxac24/AutoML_for_RAG-publicupdated this year
AutoML for RAG — recommends, builds and evaluates custom RAG sub-environments; MCP server + Gradio web UI.
MIT -
MCP server for the MLoop CLI — lets AI clients run AutoML training and prediction tasks
npm MIT -
Agent-native, local-first AutoML for tabular data. Automatic leakage guardian, reproducible recipes & native MCP server for AI agents. 🐈⚡
Apache-2.0 ★ 2 -
Agentic AutoML Platform. Upload a CSV and a LangGraph agent writes the Python, runs it in a sandboxed Docker Jupyter kernel, and checks its own output across seven workspace phases. Each phase sees only the tool schemas it needs, twelve of them served over MCP. React, Express, Postgres with pgvector. Link is the landing site; the app runs locally.
GPL-3.0 -
Judge visualization value and turn chart evidence into machine-learning actions.
MIT -
A junior ML engineer agent: profiles tabular data, checks leakage, trains vs baselines, deterministic review, report + model card. MCP tools, FastAPI.
MIT ★ 1 -
Self-hosted tabular ML that doesn't lie. Leakage Guard, conformal intervals, profit-optimized thresholds, counterfactuals & instant REST/MCP API.
MIT ★ 8 -
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 -
breezemlgithub.com/venomez-viper/breezemlupdated this year
A beginner-friendly, production-aware ML workflow layer for students, analysts, and AI agents. Train, compare, explain, export, and deploy scikit-learn models without the boilerplate.
MIT ★ 3 -
Autonomous neural architecture search (NAS) platform: NSGA-II evolution of CNN/ViT designs, distributed GPU worker mesh, agentic Groq + Gemini swarm, MCP server, Wasm sandbox, mTLS. FastAPI + PyTorch + React.
MIT ★ 3 -
Python time series forecasting assistant built on skforecast: deterministic decisions, the script that ran, an optional LLM that explains them, and an MCP server for AI agents.
pypi Apache-2.0 ★ 52 -
An AI agent that trains Earth-observation models on GEO-Bench tasks on its own and carries code-measured lessons from one dataset to the next. Strands + Claude Sonnet on Amazon Bedrock. MCP server designed to plug into GoPilot: pip install gotrain
pypi MIT -
End-to-end ML toolkit automating the complete workflow — data profiling, preprocessing, feature engineering, model selection, training, validation, explainability, drift monitoring, fairness checks, and interactive HTML reporting. Includes a full CLI for zero-code ML pipelines. Python 3.10+.
pypi MIT ★ 16 -
A no code AI data science copilot. Point it at a spreadsheet and it runs the whole machine learning workflow, then explains the result in plain language. Built with scikit learn, LangGraph, RAG, and MCP, with a leakage safe pipeline and a human in the loop.
MIT ★ 1