mcp-graph-workflow

Overview

mcp-graph-workflow is a local-first CLI tool that creates SQLite-based task graphs from PRD text files. It provides 54 MCP tools to manage the task lifecycle through 9 phases from ANALYZE to LISTENING. The solution addresses common AI coding problems by providing persistent memory, structured workflows, and traceability without requiring cloud dependencies or API keys.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• import_prd

  Reads PRD text file and creates tasks with acceptance criteria in the graph

  Try:Import requirements from my-prd.md into the workflow graphTry:Convert my product requirements document into tasks
• start_task

  Starts working on a specific task from the graph with compressed context

  Try:Start working on task 42Try:Begin implementing feature from my graph
• finish_task

  Finishes a task after validating done criteria and updates status

  Try:Mark task 15 as done with validationTry:Complete the current implementation task
• next

  Gets the next available task for the agent to work on

  Try:What's the next task I should work on?Try:Show me the next task in my workflow
• status

  Shows the current state of the task graph

  Try:Show me the current status of all tasksTry:What tasks are in progress?

Comparable tools

Installation

npm install -g @mcp-graph-workflow/mcp-graph

{
  "mcpServers": {
    "mcp-graph": {
      "command": "npx",
      "args": ["-y", "@mcp-graph-workflow/mcp-graph"]
    }
  }
}

mcp-graph init

FAQ

Does this require cloud services or API keys?

No, it's designed to be 100% local with zero cloud dependency. LLM integration is opt-in.

Can this integrate with my existing IDE?

Yes, it provides 130+ REST endpoints for IDE integration and includes a React dashboard for visualization.

Compare mcp-graph-workflow with