Workflow MCP Server

MCP server providing task evaluation, environment safety checks, and reasoning tools for AI assistants.

Features

evaluate_task: Assess task complexity (4 criteria: multi-step, unclear requirements, subtasks, bug risk)
env_verify: Validate package installation safety before execution
think: Log complex reasoning processes

Installation

npm install npm run build

Usage

Development

npm run dev

Production

npm start

Docker

docker build -t ai-workflow-mcp . docker run ai-workflow-mcp

Configuration

Add to your MCP client config (e.g., Claude Desktop):

{ "mcpServers": { "ai-workflow": { "command": "node", "args": ["/path/to/mcp/dist/server.js"] } } }

Task Evaluation Criteria

Flags ≥ 2 → Build memory-bank/

Multi-step? (requires multiple implementation steps)
Unclear requirements? (needs clarification)
Can break into subtasks? (independent components)
Cannot guarantee bug-free? (high complexity/edge cases)

License

MIT

Deploy Server

HTTP connection URL

A

security – no known vulnerabilities

-

license - not tested

A

quality - confirmed to work

How are these scores calculated?

Tools

Enables AI assistants to evaluate task complexity, verify package installation safety, and log complex reasoning processes. Provides structured assessment of multi-step tasks and environment validation for safer code execution workflows.

Workflow MCP Server

Workflow MCP Server

Features

Installation

Usage

Development

Production

Docker

Configuration

Task Evaluation Criteria

License

Tools

New MCP Servers

MCP directory API