🔄 Workflow Orchestration MCP Server

A Model Context Protocol (MCP) server for AI agent workflow orchestration. Create structured, fidelity-enforced workflows that agents discover, navigate, and execute to fulfill user goals.

Docs Site • Quick Start • Architecture • Schemas • API • Workflow Fidelity • Development • Docs Map • Workflows • Engineering

🎯 Overview

Workflow Server guides AI agents through structured, multi-step workflows. A single always-applied IDE rule bootstraps the agent — from there, the server handles workflow discovery, session management, and step-by-step navigation.

How It Works

1. Discover — The agent calls discover to learn available workflows and the bootstrap procedure

2. Start session — start_session returns a session token; get_workflow returns the workflow structure, the workflow's techniques.workflow bundled under techniques and rules, and the initialActivity ID

3. Navigate — next_activity advances the session to the next activity; get_activity returns the activity's full definition (steps, checkpoints, transitions) along with the activity's bundled techniques — the workflow's inherited techniques.activity plus the activity's own techniques[] — under techniques and rules. get_resource lazy-loads reference material referenced by a technique

4. Execute — The agent works through activities, with checkpoints for user decisions and transitions governing the flow between activities

Architecture

User Goal → Workflow → Activities → Techniques → Tools

• Workflows define the overall process (e.g., implement a feature from issue to merged PR)

• Activities are phases within a workflow (e.g., plan, implement, review, validate)

• Techniques are markdown definitions of a capability, with optional rules

• Tools are the operations the agent invokes

MCP Tools at a Glance

The server registers 17 MCP tools across five concerns. See docs/api-reference.md for full signatures.

Related MCP server: Agent Workflow MCP Server

🚀 Quick Start

Prerequisites

• Node.js 18+

• MCP Client (Cursor or Claude Desktop)

Installation

# Clone and build
git clone https://github.com/m2ux/workflow-server.git
cd workflow-server
npm install

# Set up workflow data (worktree for orphan branch)
git worktree add ./workflows workflows

# Build the server
npm run build

Configure MCP Client

Cursor (~/.cursor/mcp.json):

{
  "mcpServers": {
    "workflow-server": {
      "command": "node",
      "args": ["/path/to/workflow-server/dist/index.js"],
      "env": {
        "WORKFLOW_DIR": "/path/to/workflow-server/workflows",
        "WORKFLOW_WORKSPACE": "/path/to/your/project"
      }
    }
  }
}

WORKFLOW_WORKSPACE is required: it points at the project whose .engineering/artifacts/planning/ folder holds session state (--workspace=PATH on the command line works too). Restart your MCP client. See SETUP.md for other IDEs.

Deploy to Your Project

To set up the engineering branch pattern in your own project:

curl -O https://raw.githubusercontent.com/m2ux/workflow-server/main/scripts/deploy.sh
chmod +x deploy.sh && ./deploy.sh

This creates a .engineering/ folder with workflows and artifact directories. See SETUP.md for options and details.

Setup IDE Rule

Add the bootstrap rule from docs/ide-setup.md to your IDE's 'always-applied' rule set. The rule tells the agent to call discover on every workflow request so the bootstrap procedure stays in sync with the server.

Execute a Workflow

Tell the agent what you want to do using natural language:

Start a workflow:

Start a new work-package workflow for implementing user authentication

Begin a work-package workflow for issue #42

Resume a workflow:

Resume the work-package workflow we were working on

Continue the authentication work package from where we left off

End a workflow:

End the current work-package workflow

Complete the work package and clean up

The agent matches your request to the appropriate activity and guides you through the structured phases.

Engineering layout

The .engineering/ directory holds engineering artifacts and workflow-related assets.

Directory structure

• artifacts/planning/ — Work package plans and specifications

• history/ — Project history and change logs

• scripts/ — Utility scripts

📜 License

MIT License - see LICENSE for details.