Bi-directional traceability for AI-assisted development: 8-phase spec-driven chain, 7 gates.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
One-click editor setup isnβt available for this listing yet β we donβt have a confirmed install command, and weβd rather show nothing than point your editor at the wrong package or host. Follow the projectβs own setup instructions, linked above.
From vision to verified impact β an AI-native, fully autonomous software development methodology.
Provide a human vision statement. The AI autonomously researches, audits your codebase, generates specs and plans, implements, and validates β with bi-directional verification at every junction to ensure nothing is missed or invented.
Then in your project:
The AI handles the rest β researching, auditing, generating specs, planning, implementing, and validating β with self-gating at 7 bi-directional verification junctions.
Tutorial β β 30-minute walkthrough building a real project.
VDD follows Goldratt's recursive Strategy-Tactic decomposition: every phase is simultaneously the Tactic for its parent and the Strategy for its child.
| Phase | S&T Role | Output |
|---|---|---|
| 0. Constitution | (pre-chain) | constitution.md β Immutable project rules |
| 1. Vision | L1 Strategy: What impact? | vision.md β Impact model, success metrics |
| 2. Strategy | L1 Tactic β L2 Strategy | strategy.md β Research, 12 pillars, risk register |
| 3. Tactics | L2 Tactic β L3 Strategy | tactics.md β Codebase audit, 38 action items |
| 4. Specs | L3 Tactic β L4 Strategy | spec.md β MoSCoW acceptance criteria |
| 5. Plan | L4 Tactic β L5 Strategy | plan.md, data-model.md, contracts/ |
| 6. Tasks | L5 Tactic β L6 Strategy | tasks.md β Test-first atomic tasks |
| 7. Implement | L6 Tactic β L7 Strategy | Code β Per-task commits with full traceability |
| 8. Validate | L7 Tactic β Did it work? | impact-report.md β Drift + impact verification |
7 bi-directional gates verify both directions at every junction (108 total checks). Each gate validates 4 S&T assumptions: Necessity, Achievability, Sufficiency, Warnings.
Every code commit traces back to the original vision statement:
| Command | Phase | Action |
|---|---|---|
/vdd:init | 0 | Generate constitution.md from project context |
/vdd:vision "statement" | 1 | Expand freeform vision β structured vision.md |
/vdd:strategize | 2 | Load domain primers, spawn research subagents, synthesize strategy.md |
/vdd:tactics | 3 | Audit repo β gap analysis β tactics.md |
/vdd:specify <ID | "desc"> | 4 | Generate spec.md (or freeform β skips V/S/T) |
/vdd:clarify <feature> | 4 | Clarification pass on a spec |
/vdd:plan <feature> | 5 | Generate plan.md, data-model.md, contracts/ |
/vdd:tasks <feature> | 6 | Generate tasks.md |
/vdd:get-next-task <feature> | 7 | Extract next uncompleted task |
/vdd:implement <task-id> | 7 | Execute single task, verify, commit |
/vdd:validate | 8 | Full-chain traceability + drift + impact report |
/vdd:trace | any | Bidirectional traceability matrix |
/vdd:analyze <feature> | any | Cross-artifact consistency analysis |
/vdd:amend "what changed" | any | Cascade requirement change through full chain |
/vdd:detect-environment | any | Report per-phase tool/MCP requirements + available capabilities |
/vdd:e2e "vision statement" | 0β8 | End-to-end: run full 8-phase chain in one call, writes all 10+ template files |
/vdd:e2e -clone <domain> | 7 | Clone: crawl site (browserless/fetch) into a full dataset + exact UI/UX + rebuilt backend + generated schema + AI tools + deployable dynamic site (vdd/clone-site/) from a domain (https/http/www/bare) |
To run the MCP server locally (stdio) instead of the hosted endpoint:
OpenCode (opencode.json):
Claude Desktop (claude_desktop_config.json):
VDD is available as a public MCP server at https://vdd.simonmak.com β 15 tools, no API key required β over the MCP Streamable HTTP transport at https://vdd.simonmak.com/api/mcp (also reachable at /mcp). The legacy SSE endpoint is retired: https://vdd.simonmak.com/api/sse now returns an HTTP 308 redirect to /api/mcp.
OpenCode β add to opencode.json:
Claude Desktop β add to claude_desktop_config.json:
Cursor β add MCP server URL: https://vdd.simonmak.com/api/mcp
Any Streamable HTTP client (Smithery, Claude Code, β¦) β MCP server URL: https://vdd.simonmak.com/api/mcp
vdd_init, vdd_vision, vdd_strategize, vdd_tactics, vdd_specify, vdd_clarify, vdd_plan, vdd_tasks, vdd_get_next_task, vdd_implement, vdd_validate, vdd_inspect, vdd_amend, vdd_clone, vdd_detect_environment.
The one-call e2e shortcut is not an MCP tool (it duplicates the phase sequence); use the CLI vdd e2e "vision" instead.
All tools accept: statement, projectRoot, actionItemId, feature, taskId, description, availableTools, capabilities, researchFindings, artifactFiles.
The server is listed on Glama, which builds it from source and publishes a hosted remote endpoint plus a Tool Definition Quality Score and maintenance rating:
Maintainer notes:
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/vision-driven-design)<a href="https://allmcps.com/mcp/vision-driven-design"><img src="https://allmcps.com/api/badge/vision-driven-design?style=directory" alt="Vision Driven Design on AllMCPs" /></a>