mcp-graph-workflow
Active·★ 41·MIT·Updated 2026-05-22
A local-first CLI tool that converts product requirement documents (PRD) into structured task graphs with AI-powered context, semantic search, and multi-agent orchestration. It integrates with MCP clients like GitHub Copilot, Claude, and Cursor, offering a web dashboard, sprint planning, and token-efficient context compression.
#agent-tooling#agentic-workflows#ai-tools#cli#local-first#mcp#mcp-server#mcp-servers
01
Features
01PRD to Task Graph
02AI-Optimized Context with 70-85% token reduction
03Smart Task Routing via 'next' command
04Semantic Search + RAG (BM25, TF-IDF)
05Web Dashboard with interactive graph visualization
02
Compatibility
GitHub Copilot
GitHub Copilot
Verified via docs
Claude Code
Claude Code
Verified via docs
Cursor
Cursor
Verified via docs
IntelliJ
IntelliJ
Verified via docs
Windsurf
Windsurf
Verified via docs
Zed
Zed
Verified via docs
03
Quick start
1
$ npx -y @mcp-graph-workflow/mcp-graph
04
Use cases
↳AI Engineers: structured agentic workflows with token-efficient context
↳Tech Leads: PRD decomposition into trackable, dependency-aware task graphs
↳Solo Developers: project planning with AI-powered suggestions and progress tracking
05
Alternatives
factorly★ 24
Factorly is a local runtime for agent tool chains. It manages tool calls, injects credentials from an encrypted vault, enforces governance rules, and logs everything. Your agent sees workflows, tools, and data. Secrets stay secret.
drift★ 791
Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI.
android-remote-control-mcp★ 734
An MCP Server for Android running on the phone, optmized for token usage, supports also files downloads and cloudflare (free) and ngrok automated tunnelling.
Comments
Log in to leave a comment
No comments yet. Be the first!