Workflows MCP
Model Context Protocol server that enables AI agents to discover, create, and execute complex, multi-step workflows defined in simple YAML files. Allow your AI agents to better organize their tool usage and provide a more structured way to handle com
What is Workflows MCP?
Workflows MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol server that enables ai agents to discover, create, and execute complex, multi-step workflows defined in simple yaml files. allow your ai agents to better organize their tool usa...
Model Context Protocol server that enables AI agents to discover, create, and execute complex, multi-step workflows defined in simple YAML files. Allow your AI agents to better organize their tool usage and provide a more structured way to handle com
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Model Context Protocol server that enables AI agents to disc
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @fiveohhwon/workflows-mcpManual Installation
npx -y @fiveohhwon/workflows-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Workflows MCP
workflows-mcp is a Model Context Protocol server that lets AI agents discover, create, and execute complex multi-step workflows defined in simple YAML files. Instead of issuing one-off tool calls, agents can persist reusable workflows with branching, looping, parallel execution, and checkpoint support, making multi-step automation reproducible and version-controlled. Developers use it to organize AI tool usage into structured, reliable sequences that can be rolled back, iterated, and shared across sessions.
Prerequisites
- Node.js 18 or later installed
- An MCP-compatible client such as Claude Desktop, Cursor, or VS Code with MCP support
- npm or npx available in your terminal (comes with Node.js)
Install the server via npx (no install required)
The server is published to npm as @fiveohhwon/workflows-mcp. You can run it directly with npx without a global install.
npx -y @fiveohhwon/workflows-mcpAdd the server to your MCP client configuration
Edit your MCP client config file. For Claude Desktop on macOS, the file is ~/Library/Application Support/Claude/claude_desktop_config.json.
{
"mcpServers": {
"workflows": {
"command": "npx",
"args": ["-y", "@fiveohhwon/workflows-mcp"]
}
}
}Restart your MCP client
Restart Claude Desktop or your chosen MCP client so it picks up the new server and connects to it.
Create your first workflow
Ask the AI to create a workflow. The server exposes the create_workflow tool, which accepts a name and a list of steps with action types like tool_call, analyze, branch, loop, parallel, checkpoint, and retry.
Execute a workflow step by step
Start a workflow with start_workflow and then advance through it with run_workflow_step, passing results from each step to the next. Use get_workflow_versions and rollback_workflow to manage history.
Workflows MCP Examples
Client configuration
Minimal Claude Desktop configuration to connect to workflows-mcp via npx.
{
"mcpServers": {
"workflows": {
"command": "npx",
"args": ["-y", "@fiveohhwon/workflows-mcp"]
}
}
}Prompts to try
Example prompts for creating and running multi-step workflows.
- "Create a workflow called 'Code Review' that reads a file, analyzes it, then writes a summary"
- "List all my saved workflows and show their step counts"
- "Start the 'Deploy Pipeline' workflow with file_path set to src/main.py"
- "Roll back the 'Data Processing' workflow to version 2"
- "Create a workflow with a branch step: if analysis finds errors, run the fix step, otherwise checkpoint and finish"Troubleshooting Workflows MCP
npx command hangs or takes too long on first run
npx must download the package on the first run. If it hangs, check your internet connection and npm registry access. You can speed up future runs by installing globally: 'npm install -g @fiveohhwon/workflows-mcp'.
Workflows created in one session are not visible in the next
Workflow storage location depends on where the server stores its data. Check if a workflows directory was created in the working directory from which npx was invoked, and ensure subsequent sessions start from the same directory.
run_workflow_step returns an error about invalid step ID
Always call start_workflow first to create an execution session, then pass the returned session ID and the correct step ID to run_workflow_step. Use get_workflow to inspect the step IDs before executing.
Frequently Asked Questions about Workflows MCP
What is Workflows MCP?
Workflows MCP is a Model Context Protocol (MCP) server that model context protocol server that enables ai agents to discover, create, and execute complex, multi-step workflows defined in simple yaml files. allow your ai agents to better organize their tool usage and provide a more structured way to handle com It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Workflows MCP?
Install via npm with the command: npx -y @fiveohhwon/workflows-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Workflows MCP?
Workflows MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Workflows MCP free to use?
Yes, Workflows MCP is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Workflows MCP Alternatives — Similar Coding Agents Servers
Looking for alternatives to Workflows MCP? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Workflows MCP 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 Workflows MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.