@mcp-graph-workflow/mcp-graph
v5.34.2
Published
MCP local-first PRD to task graph — transforms text into executable structure
Maintainers
Readme
@mcp-graph-workflow/mcp-graph
Automate project planning from PRD to execution. Local-first CLI that converts product requirement documents into structured task graphs with AI-powered context, semantic search, and multi-agent orchestration.
Quick Start
GitHub Copilot (VS Code)
Create .vscode/mcp.json in your project:
{
"servers": {
"mcp-graph": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@mcp-graph-workflow/mcp-graph"]
}
}
}Enable Agent Mode in Copilot Chat, then use the tools: init → import_prd → next → context → update_status
Claude Code / Cursor / IntelliJ
Add to .mcp.json:
{
"mcpServers": {
"mcp-graph": {
"command": "npx",
"args": ["-y", "@mcp-graph-workflow/mcp-graph"]
}
}
}Windsurf / Zed / Other MCP Clients
Use stdio transport with:
npx -y @mcp-graph-workflow/mcp-graphFrom Source
git clone <repo-url> && cd mcp-graph-workflow
npm install && npm run build
npm run dev # HTTP + dashboard at localhost:3000For detailed setup, see Getting Started.
Features
- PRD → Task Graph — Import .md, .txt, .pdf, or .html documents and auto-generate hierarchical task trees
- AI-Optimized Context — 70-85% token reduction with tiered compression (summary/standard/deep)
- Smart Task Routing —
nextsuggests the best task based on priority, dependencies, and blockers - Semantic Search + RAG — Full-text BM25 search + TF-IDF embeddings, 100% local
- Sprint Planning — Velocity metrics, capacity-based planning, risk assessment
- Web Dashboard — Interactive graph visualization, backlog tracking, code intelligence, insights
- Multi-Agent Mesh — Serena + GitNexus + Context7 + Playwright coordinated via event bus, with phase-aware MCP suggestions
- Environment Doctor —
mcp-graph doctorvalidates Node.js, SQLite, permissions, integrations, and suggests fixes - Local-First — SQLite persistence, zero external dependencies, cross-platform
Who is this for?
| Persona | Use Case | |---------|----------| | 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 | | Teams using Copilot/Claude/Cursor | MCP-native tool integration for AI-assisted development |
Dashboard
6 tabs: Graph (interactive diagram + filters) · PRD & Backlog (progress tracking) · GitNexus (code intelligence) · Serena (code memories) · Insights (bottlenecks + metrics) · Benchmark (token economy)
mcp-graph serve --port 3000 # or: npm run devTools & API
| | Count | Reference | |---|---|---| | MCP Tools | 45 + 6 deprecated | MCP-TOOLS-REFERENCE.md | | REST Endpoints | 135 (26 routers) | REST-API-REFERENCE.md |
| CLI Commands | 6 | init, import, index, stats, serve, doctor |
Integrations
| Integration | Role | |-------------|------| | Code Intelligence | Native LSP-based code analysis, symbol navigation, multi-language | | Context7 | Up-to-date library documentation fetching | | Playwright | Browser-based task validation and A/B testing |
Native systems: Code Intelligence (code analysis), Native Memories (project knowledge). See INTEGRATIONS-GUIDE.md.
Testing
4200+ tests across 390 Vitest files + Playwright E2E specs.
npm test # Unit + integration
npm run test:e2e # Browser E2E (Playwright)
npm run test:all # EverythingDocumentation
| Document | Description | |----------|-------------| | Getting Started | Step-by-step guide for new users | | Architecture | System layers, modules, data flows | | MCP Tools Reference | 46 tools + 6 deprecated, full parameters | | REST API Reference | 19 routers, 59 endpoints | | Knowledge Pipeline | RAG, embeddings, context assembly | | Integrations | Code Intelligence, Context7, Playwright | | Test Guide | Test pyramid and best practices | | PRD Writing Guide | How to write PRDs that import correctly | | Lifecycle | 8-phase dev methodology |
Support the Project
If this tool is useful to you, consider supporting its development:
- Star this repo — it helps others discover the project
- Share — tell your team, post on X/LinkedIn, write about it
- Contribute — see CONTRIBUTING.md. TDD is mandatory — write the failing test first
- Sponsor — GitHub Sponsors
