Browse
→ AI & Models
→ MFlowy
MFlowy
MCP-native modular machine-learning workflow engine that exposes data profiling, analysis, model training and prediction capabilities as discoverable MCP tools. YAML-configured DAG workflows, local and delegated job providers, and pyfunc/CLI/server entry points let agents assemble traceable ML experiments without reading bespoke integration docs. Public GitHub repository created August 22, 2026.
MCP unverified
Integration
| Transport | stdio |
| Auth | none |
| Endpoint | https://github.com/ifoodsci-ai/mflowy |
| Install | uvx --from "mflowy[stats]" mcpSrv |
Use Cases
| 01 | Let an autonomous data-science agent discover available analysis and modeling tools through MCP |
| 02 | Run traceable data profiling, training and prediction jobs from YAML-defined workflows |
| 03 | Delegate heavier model training while keeping analysis tools callable through one MCP surface |
Tags
machine-learning data-analysis workflow dag mlflow xgboost python uvx
Machine-readable: /api/servers.json
· JSON-LD schema embedded in <head>