Flow Like
Flow-Like: Strongly Typed Enterprise Scale Workflows. Built for scalability, speed, seamless AI integration and rich customization.
What is Flow Like?
Flow Like is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to flow-like: strongly typed enterprise scale workflows. built for scalability, speed, seamless ai integration and rich customization.
Flow-Like: Strongly Typed Enterprise Scale Workflows. Built for scalability, speed, seamless AI integration and rich customization.
This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Flow-Like: Strongly Typed Enterprise Scale Workflows. Built
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx flow-likeConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Flow Like
Flow-Like is a strongly-typed, enterprise-scale workflow automation platform that integrates AI natively through a visual drag-and-drop node editor. It ships with 900+ built-in nodes covering APIs, databases, file processing (Excel, CSV, PDF), messaging (Slack, Discord, email), local and cloud LLM execution, IoT, and more — all with complete data lineage tracking. The platform runs entirely on your own hardware (desktop, server, or phone) or can be embedded as a white-label SaaS product, giving teams full control over data while building production-grade AI pipelines without writing low-level code.
Prerequisites
- For the desktop app: macOS, Windows, or Linux desktop environment
- For building from source: Rust toolchain, Bun package manager, Tauri dependencies, and the Protobuf compiler
- For the hosted web app: a modern browser and an account at app.flow-like.com
- For self-hosted enterprise deployment: Docker and an OIDC-compatible identity provider for SSO
Download and install the desktop app
The easiest way to get started is to download the pre-built desktop installer for your operating system from the official download page.
# Visit https://flow-like.com/download
# Download the installer for macOS, Windows, or Linux
# Run the installer and launch Flow-LikeAlternatively, try the web app
Access Flow-Like directly in the browser without installing anything by visiting the hosted web application.
# Navigate to https://app.flow-like.com in your browserBuild from source (optional, for contributors)
Clone the repository and build the desktop app using Bun and Tauri. Ensure Rust and Bun are installed first.
git clone https://github.com/TM9657/flow-like.git
cd flow-like
bun install
bun run build:desktopCreate your first workflow
Open the visual workflow editor and drag nodes from the 900+ built-in library onto the canvas. Connect node pins using the type-aware connector system — mismatched types are flagged before the workflow runs.
Add an AI node and configure a model
Add an LLM node from the AI category. Choose a local model (runs on your hardware) or configure a cloud provider endpoint. Connect the model output to downstream processing nodes to build an AI-powered pipeline.
Enable MCP integration
In the Flow-Like settings panel, enable the MCP client or server feature to expose your workflows as MCP tools or to consume external MCP servers as nodes within your pipelines.
Flow Like Examples
Client configuration
If Flow-Like exposes an MCP server endpoint, connect to it from Claude Desktop using npx flow-like as the command.
{
"mcpServers": {
"flow-like": {
"command": "npx",
"args": ["flow-like"]
}
}
}Prompts to try
Use these prompts when interacting with a Flow-Like-connected AI agent.
- "Run the 'customer onboarding' workflow with the data from the uploaded CSV file."
- "Trigger the Slack notification workflow and send a summary to the #alerts channel."
- "Process the PDF report using the document extraction pipeline and return the key figures."
- "List all available workflows and show me the input schema for the data-enrichment pipeline."Troubleshooting Flow Like
Build fails with Tauri or Protobuf compilation errors
Follow the platform-specific setup guide at https://docs.flow-like.com/contributing/getting-started/ to install all native dependencies. On macOS, 'brew install protobuf' resolves most Protobuf errors.
LLM node fails to run a local model
Ensure your machine meets the VRAM or RAM requirements for the selected model. For CPU-only inference, choose a smaller quantized model (e.g. Q4_K_M). Check the Flow-Like logs panel for the specific error from the inference engine.
Workflow runs but data does not flow between nodes
Check that connected pin types match — Flow-Like enforces strong typing. Mismatched types turn the connector red. Add a type-conversion node between incompatible pins.
Frequently Asked Questions about Flow Like
What is Flow Like?
Flow Like is a Model Context Protocol (MCP) server that flow-like: strongly typed enterprise scale workflows. built for scalability, speed, seamless ai integration and rich customization. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Flow Like?
Follow the installation instructions on the Flow Like GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Flow Like?
Flow Like works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Flow Like free to use?
Yes, Flow Like is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Flow Like Alternatives — Similar Business Applications Servers
Looking for alternatives to Flow Like? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.
n8n
★ 189.1kA comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou
LobeHub
★ 77.5k🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Jeecgboot
★ 46.4kAI 低代码平台，「低代码 + 零代码」双模式驱动：低代码一键生成前后端代码，零代码 5 分钟搭建系统，AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，消除 Java 项目 80% 的重复工作，提效而不失灵活。
CowAgent
★ 44.7kCowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。
Minds Platform
★ 39.2kPlatform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.
Astrbot
★ 32.8kAI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Browse More Business Applications MCP Servers
Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Flow Like in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Flow Like?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.