MFlowy
MFlowy 数据建模分析工作流
MFlowy 是一个 MCP-native 的模块化 ML 工作流引擎:基于 DAG 分层执行,配置驱动,支持从数据处理、模型训练到可视化分析的可跟踪、可追溯工作流。
核心特性
MCP-native:全部能力以 MCP 工具(pyfunc)暴露,同一套工具经三种入口调用——MCP server(stdio)、JSON runner CLI(
cmd)、直接 import(宿主内嵌)DAG 工作流编排:支持复杂的有向无环图(DAG)拓扑结构,灵活定义任务依赖关系
配置驱动:通过 YAML 配置文件定义工作流,无需编写代码
装饰器注册:纯函数 +
@handler装饰器自动注册,新增功能只需创建.py文件中间件系统:责任链模式处理横切关注点(数据注入、mlflow 记录、错误即停、各类日志)
数据血缘:MLflow tag(
mflowy.input_steps)自动记录步骤间输入依赖可观测执行:MLflow 全量追踪(参数/指标/模型/产物)+ 结构化
WorkflowResult(逐节点 run_id/状态/输出);过程日志绑定 stderr,终端模式下按级别着色可扩展执行策略:JobProvider 契约抽象 compute 工具的执行环境,内置本地实现,远程执行由自定义实现接入(见 docs/REMOTE_MODELING.md)
Related MCP server: Procesio MCP Server
架构与调用方式
MFlowy 以 MCP 为架构主体:src/mflowy/mcp/tools.py 定义全部 compute 工具(eda / modeling / explanation / predict / inverse_optimization 等),经三种入口调用:
入口 | 命令 | 场景 |
MCP server(stdio) |
| MCP 客户端(Claude Code、Cursor 等)接入 |
JSON runner(CLI) |
| 命令行、K8s Job 容器、subprocess |
直接 import |
| 宿主程序内嵌调用 |
CLI(
cmd)是 MCP 工具层的命令行通道,与 MCP server 共享同一套工具实现与 JobProvider 委派,不是独立架构;历史独立 CLI(mflowy run/validate/list-modules等)已废弃。
快速开始
# 构建 wheel(→ dist/mflowy-<version>-py3-none-any.whl)
make build-whl
# MCP server (stdio) — 完全体(数据分析 + 建模);<whl> 为 wheel 绝对路径(见下方说明)
uvx --index-strategy unsafe-best-match \
--default-index https://mirrors.aliyun.com/pypi/simple/ \
--index https://download.pytorch.org/whl/cpu \
--from "mflowy[modeling] @ file://<whl绝对路径>" \
mcpSrv
# JSON runner(CLI)— 本地调试
uv run cmd list_modules # 查看支持的步骤及模块列表(base,无数据栈)
uv run cmd list_modules '{"step":"load"}' # 查看 load 步骤的模块列表
uv run cmd get_module_info '{"step":"load","module":"csv"}' # 查看 load 步骤的 csv 模块信息
uv run --extra stats cmd data_profile '{"file_path": "..."}' # 数据分析工具
uv run --extra modeling cmd modeling '{"modeling_steps_yaml": "...", "name": "...", "desc": "..."}' # 建模工具环境变量
变量 | 用途 | 示例 |
| Tracking server URI(未设置时 workflow 与查询工具同落固定库 |
|
| JobProvider 解析: |
|
| 自定义 JobProvider 模块的包根 |
|
| 遥测模式: |
|
MCP 客户端配置示例
{
"mcpServers": {
"mflowy": {
"type": "stdio",
"command": "uvx",
"args": [
"--index-strategy", "unsafe-best-match", // torch CPU 索引必需(见下方说明)
"--default-index", "https://mirrors.aliyun.com/pypi/simple/", // 可选:包索引镜像(网络可达 PyPI 时省略)
"--index", "https://download.pytorch.org/whl/cpu", // [modeling] 需要;仅 [stats] 可省略
"--from", "mflowy[modeling] @ file:///path/to/mflowy-<version>-py3-none-any.whl",
"mcpSrv"
],
"env": {
// "PYTHONPATH": "/path/to/custom_module_parent",
// "MFLOWY_JOB_PROVIDER": "<custom_module>:<class>",
// "MLFLOW_TRACKING_URI": "postgresql://user:pwd@host:5432/mlflow"
}
}
}
}启动说明
入口名
mcpSrv:刻意避开 mcp SDK 自带的同名mcpCLI(mcp.cli:app)——uvx 解析mcp命令时可能命中 SDK 侧导致启动失败extras 内联在
--fromspec:uvx 的--extra需新版 uv,内联写法兼容性最好<whl>为绝对路径:make build-whl产出dist/mflowy-<version>-py3-none-any.whl,版本号变更需同步torch CPU 索引(
--indexpytorch-cpu +--index-strategy unsafe-best-match)为 [modeling] 必需:uvx 不读 pyproject 的[tool.uv.sources],缺省时 torch 解析为 CUDA 全家桶(2–3GB);unsafe-best-match须与 pytorch 索引同用,否则 first-index 策略会因该索引上的旧版 requests 解析失败开发态可跳过 wheel:仓库根目录
.mcp.json.example为源码路径形式,始终最新
遥测(Telemetry)
MCP 工具调用诊断采集,同意制、默认 ask,端点不可达时完全透明不影响工具调用,仅覆盖 MCP 入口。隐私契约见 PRIVACY.md,接入与配置详情见 docs/TELEMETRY.md。
贡献
欢迎任何形式的贡献(功能、修复、文档、案例)。请阅读 CONTRIBUTING.md(开发流程与约定)、CODE_OF_CONDUCT.md、PRIVACY.md(遥测隐私契约)与 SECURITY.md(漏洞披露)。
许可证
本项目基于 MIT License 开源。
文档
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables management of multiple N8N workflow automation instances through MCP. Supports listing, creating, updating, deleting, executing workflows and monitoring their executions across different N8N environments.63MIT
- AlicenseBqualityDmaintenanceEnables interaction with the Procesio automation platform to list, view, and manage workflows. It allows users to launch process instances and monitor their status through MCP-compatible clients.12Apache 2.0

Patronus MCP Serverofficial
AlicenseNot gradedqualityDmaintenanceEnables running LLM evaluations, experiments, and custom evaluators through a standardized MCP interface.16Apache 2.0- AlicenseNot gradedqualityDmaintenanceMCP Server for interacting with the Langflow API via a natural language interface. It exposes Langflow functionalities as tools for LLMs.MIT
Related MCP Connectors
Create, browse, remix, collaborate on, and run durable AI workflow nodes from MCP hosts.
MCP Hub: AI service discovery, per-user OAuth, and multi-service workflow orchestration
MCP Server for agents to onboard, pay, and provision services autonomously with InFlow
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ifoodsci-ai/mflowy'
If you have feedback or need assistance with the MCP directory API, please join our Discord server