io.github.juanklagos/sdd-mcp MCP Server
io.github.juanklagos/sdd-mcp
Spec-Driven Development workflow: write and approve specs before code, with validation gates and bilingual guides.
What is the io.github.juanklagos/sdd-mcp MCP server?
The sdd-mcp MCP server is a Spec-Driven Development (SDD) workflow tool that enforces the rule 'no code before approved spec' through validation scripts, decision logging, and AI-agent integration. It provides commands to create specs, validate consistency, run approval gates, and maintain a logbook of decisions across bilingual (EN/ES) projects.
This server brings Spec-Driven Development to AI agents and teams. It manages the complete SDD workflow: writing specifications, validating them against plans, enforcing approval gates, and recording decisions in a logbook. Use it to ensure decisions are documented in files rather than lost in chat history, maintain consistency across multi-agent projects, and create an auditable record of why features were built the way they were.
How to install io.github.juanklagos/sdd-mcp
Copy-paste configuration for popular MCP clients.
SDD_PROJECT_ROOTPath to the SDD workspace (project with specs/ or a spec/ sidecar). Defaults to the current working directory.
SDD_WORKSPACES_ROOTWhere sdd_create_workspace creates ./www/<project-name>. Defaults to the current working directory.
Tools & capabilities
Tools this server exposes to the agent.
sdd:help— Tells you what stage you are in and the single next stepsdd:new— Guided start: idea → first spec ready for approvalsdd:spec— Create or refine a spec bundle with EARS criteriasdd:gate— Runs the gate — approval, plan consistency, consent — and records yourssdd:decision— One decision, written down in bitacora/decisiones/: what, why, what was rejected, when to revisitsdd:close— Validates and closes the session with the output contractsdd:tutor— A conversational SDD course by levels, graded by the real validation scriptscheck-sdd-policy.sh— Multi-agent policy files are alignedcheck-sdd-gate.sh— Spec approved + plan consistent + consent recordedvalidate-sdd.sh— Validate SDD structuregenerate-status.sh— Status dashboardnew-spec.sh— Create a new spec bundle
Use cases
- Write and approve feature specifications before implementation begins, ensuring decisions are documented and traceable
- Validate that implementation plans are consistent with approved specifications and catch misalignments early
- Enforce multi-agent governance: check that all AI agents and team members are working from the same approved specs and plans
- Maintain a decision logbook (bitacora) that records what was decided, why alternatives were rejected, and when to revisit choices
- Run approval gates in CI/CD pipelines to block code merges until specs and plans are properly approved and aligned
io.github.juanklagos/sdd-mcp MCP server FAQ
SDD means writing and approving a clear specification before any code exists. Decisions are recorded in files (spec.md, plan.md) instead of buried in chat history, creating an auditable record and enabling consistent multi-agent workflows.
Yes. The template and MCP server are MIT-licensed and free to use anywhere, including commercially and inside companies, without asking permission.
Run `npx @juanklagos/sdd-mcp@latest connect` in your project folder. It auto-detects your clients (Claude Code, Cursor, VS Code, Windsurf, Gemini CLI, opencode) and writes the MCP configuration into each one. Restart your client to activate the slash commands.
No. The fastest way is `npx @juanklagos/create-sdd-project@latest my-app`, which scaffolds a lightweight `spec/` sidecar folder in your existing project. The full template is optional and mainly for learning or standalone workspaces.
None. The server runs locally and works with any project folder. It uses shell scripts and file I/O; no external services or API keys are needed.
Yes. Install the compact `spec/` sidecar into any existing codebase without moving or changing your current code. The SDD workflow artifacts live in `spec/` and your implementation stays where it is.
README (reference)
Source of truth, from the repository.
🌱 Spec-Driven Development Template
Learn Spec-Driven Development, then use it on real projects.<br>One rule: no code until you approve a written spec. A script checks that rule every time you run it, and prints exactly what it looked at.
🇺🇸 English · 🇪🇸 Español
<img src="https://img.shields.io/badge/version-v2.8.0-3b82f6?style=for-the-badge" alt="Version"> <img src="https://img.shields.io/badge/license-MIT-8b5cf6?style=for-the-badge" alt="License"> <a href="https://github.com/juanklagos/spec-driven-development-template/releases/tag/v2.8.0"><img src="https://img.shields.io/badge/release-latest-10b981?style=for-the-badge" alt="Latest release"></a><a href="https://juanklagos.github.io/spec-driven-development-template/"><img src="https://img.shields.io/badge/📖_Docs_Site-Browse-0ea5e9?style=for-the-badge" alt="Documentation site"></a> <a href="https://github.com/juanklagos/aprende-sdd"><img src="https://img.shields.io/badge/🎓_Course-Learn_by_doing-16a34a?style=for-the-badge" alt="Interactive course"></a> <a href="https://github.com/marketplace/actions/sdd-validate"><img src="https://img.shields.io/badge/✅_Action-Marketplace-2088FF?style=for-the-badge&logo=githubactions&logoColor=white" alt="SDD Validate on GitHub Marketplace"></a> <a href="https://codespaces.new/juanklagos/spec-driven-development-template"><img src="https://img.shields.io/badge/⚡_Codespaces-Open-181717?style=for-the-badge&logo=github" alt="Open in GitHub Codespaces"></a>
Non-technical start · Quickstart · AI agent start · Commands · Community
</div>What is this?
Spec-Driven Development (SDD) means writing and approving a clear specification before any code exists. What you decided ends up in a file, instead of buried in a chat you will close and never find again. By 2026 it is how most people build software with AI agents.
This repo does double duty.
It is a school: a bilingual (EN/ES) path that starts from zero, with guides, an interactive course and a tutor you can talk to. You do not need to know how to program to get through it.
It is also a toolkit for real work: scripts that check the rule, instruction files your AI assistant reads, a connector so your AI tool can run the workflow itself (MCP, the Model Context Protocol), and a single spec/ folder you add to a project that already has code — without moving any of it.
The step-by-step commands come from GitHub Spec Kit. This repo adds the guides, the checks and the templates on top of them.
<div align="center">The flow in action — create a spec, validate, pass the gate (regenerated on every release):
<img src="./docs/assets/demo.gif" alt="SDD flow demo: create a spec, validate the structure, pass the gate" width="720"> </div>What changes in practice: decisions stop living in chat history and move into specs/. The gate stays closed until spec.md and plan.md exist, agree, and you record your consent — a script checks that, not somebody's memory. A new teammate or a new agent lands in a folder layout they already recognize. And bitacora/ keeps the session log, so six months later you can still find out why something was done the way it was.
Want the industry map? Read SDD in 2026: state of the art and how this template compares.
Choose your door
- Non-technical (founder, PM, curious): START_HERE_NON_TECH.md — a guided start with no jargon in it.
- Developer: QUICKSTART.md — the commands to scaffold and validate, about five minutes.
- AI agent, or you pasting into one: AI_START_HERE.md — operating rules plus copy/paste prompts for each level.
Then pick your learning level. Every guide on the docs site carries its level badge:
- 🟢 Beginner: quick guide for non-programmers
- 🟡 Intermediate: team discipline guide
- 🔴 Advanced: governance and standardization
[!TIP] If you would rather learn by doing, take the interactive course (GitHub Skills format): 4 steps, ~35 min, auto-graded by Actions. Your exam is the real SDD gate.
Start in 30 seconds
Copy/paste this prompt into your AI assistant (Claude, Cursor, Copilot, Gemini...):
Using https://github.com/juanklagos/spec-driven-development-template, guide me step by step with SDD for my project.
My project is: [describe your project in plain language].
If my project is new, initialize from this template and GitHub Spec Kit as the base workflow.
If it already exists, adapt it without breaking current behavior.
No code before approved spec and consistent plan.
Built-in commands for your AI agent
If you use Claude Code, this repo ships slash commands out of the box. Start with /sdd:help:
| Command | What it does |
|---|---|
/sdd:help | Tells you what stage you are in and the single next step |
/sdd:new | Guided start: idea → first spec ready for approval |
/sdd:spec | Create or refine a spec bundle with EARS criteria |
/sdd:gate | Runs the gate — approval, plan consistency, consent — and records yours |
/sdd:decision | One decision, written down in bitacora/decisiones/: what, why, what was rejected, when to revisit |
/sdd:close | Validates and closes the session with the output contract |
/sdd:tutor | A conversational SDD course by levels, graded by the real validation scripts |
Install in any project as a plugin (no cloning):
/plugin marketplace add juanklagos/spec-driven-development-template
/plugin install sdd@sdd-template
- VS Code / Copilot: the same flows as prompt files in
.github/prompts/. - Any agent (39 tools): portable Agent Skill at skills/sdd-workflow/SKILL.md.
- AI context: llms.txt indexes all docs for coding agents (regenerate with
./scripts/generate-llms-txt.sh).
The golden rule
[!IMPORTANT] No code before an approved
spec.mdand a consistentplan.md. A script enforces this, and implementation starts only once your consent is on record.
./scripts/check-sdd-policy.sh . # multi-agent policy files are aligned
./scripts/check-sdd-gate.sh . # spec approved + plan consistent + consent recorded
./scripts/confirm-user-consent.sh --spec 001-<slug> "User approved scope X"
(In sidecar projects the same scripts live under ./spec/scripts/.)
Enforce it in CI too. This repo doubles as a GitHub Action, listed on the GitHub Marketplace:
- uses: juanklagos/spec-driven-development-template@v2.8.0
with:
path: "." # project root (sidecar or standalone auto-detected)
strict: "true"
Reference files: sdd.policy.yaml · INSTRUCTIONS.md · AGENT_OPERATING_SYSTEM.md
How it works
flowchart LR
A["💡 Idea in plain language"] --> B["📋 spec.md approved"]
B --> C["🗺️ plan.md consistent"]
C --> D["✅ tasks.md prioritized"]
D --> E["🚦 Gate + explicit consent"]
E --> F["⚙️ Implementation"]
F --> G["🔍 Validation + logbook"]
Every feature gets a numbered spec bundle, and every session leaves a trace in bitacora/ (the logbook):
spec.md— what and why (approved by you)plan.md— how (consistent with the spec)tasks.md— concrete stepshistory.md— how it evolved
Full walkthrough example: examples/002-mcp-end-to-end
Apply it to a real project
Fastest start (no clone needed):
npx @juanklagos/create-sdd-project@latest my-app
It asks a few questions and scaffolds the recommended spec/ sidecar, or a full workspace, from the latest template.
Three ways to use the template, from lightest to heaviest:
| Mode | When | Command |
|---|---|---|
Compact spec/ sidecar ⭐ | Real or existing project: SDD artifacts in ./spec/, code stays in your project root | ./scripts/install-spec-sidecar.sh /path/to/project --profile=recommended |
Internal workspace www/ | The runnable project should live inside this template repo | ./scripts/create-www-project.sh my-project codex |
| Full standalone copy | You explicitly want the whole framework as your workspace | ./scripts/init-project.sh /path/to/project --profile=full |
<details> <summary><b>Everyday commands</b> (sidecar mode shown; the same scripts exist at root in standalone mode)</summary> <br>[!TIP] The professional default is the compact
spec/sidecar and nothing else. Never copy the full framework into a real codebase unless you actually want standalone mode.
| Action | Command |
|---|---|
| New spec | ./spec/scripts/new-spec.sh "my-feature" "Owner" |
| Validate structure | ./spec/scripts/validate-sdd.sh . --strict |
| Policy check | ./spec/scripts/check-sdd-policy.sh . |
| SDD gate | ./spec/scripts/check-sdd-gate.sh . |
| Status dashboard | ./spec/scripts/generate-status.sh |
Folder anatomy and layout details: project organization map
flowchart TD
A["Your project root (code)"] --> B["spec/"]
B --> C["idea/"]
B --> D["specs/ (numbered bundles)"]
B --> E["bitacora/ (logbook)"]
B --> F["scripts/ (gate + validation)"]
</details>
<details>
<summary><b>Connect via MCP</b> (optional, advanced)</summary>
<br>
If your AI tool supports MCP (the Model Context Protocol), it can run this workflow itself: create specs, check the gate, write the logbook. One command sets it up, in your project's folder:
npx @juanklagos/sdd-mcp@latest connect
It finds the clients you have — Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, opencode — and writes the configuration into each one's own file. It merges into what you already have and never overwrites it. Add --dry-run first to see what it would touch. Then restart your client.
- Prefer doing it by hand? Point your client at npm:
{"command": "npx", "args": ["-y", "@juanklagos/sdd-mcp@latest"]}. The@latestmatters — without it,npxcan serve an old cached version with fewer tools. - Working on this template itself?
npm install && npm run build && npm run mcp:startruns the server from source. - SDD Builder (visual, drag-and-drop): build once with
npm run builder:build, thenSDD_PROJECT_ROOT=/path/to/your/project npm run mcp:http:startand openhttp://127.0.0.1:3334/builder— compose your specs as connected cards, where every card is a realspecs/NNN/bundle on disk. Inside this template repository the builder is blocked by design (no target-project work in the template root), so always pointSDD_PROJECT_ROOTat a real workspace. See the visual guide. - Already using SDD and want the latest?
npx @juanklagos/sdd-mcp@latest upgrade --project-root . --dry-runshows what would change before changing it: framework files get repaired, yours are never written without--apply. See the upgrade guide. - SDD Desk (the same builder, as a desktop app): download it for macOS, Windows or Linux. Nothing else has to be installed: the app includes everything it needs. While it is open, your AI assistant can connect to it — copy the address the app shows you and paste it into your assistant's settings. One caveat: the app is not digitally signed, so the first time you open it macOS or Windows shows a scary-looking warning and asks you to allow it. If you would rather not deal with that, run
npx @juanklagos/sdd-mcp@latest --httpinstead. Same tool, in your browser, no warning. - Visual dashboard: point the server at a project —
SDD_PROJECT_ROOT=./www/my-project npm run mcp:http:start— then openhttp://127.0.0.1:3334/dashboardfor a page you can look at but not edit: whether the gate is open, a few headline numbers, how far each spec has got, and which specs are waiting on another one. In your language, with nothing to compile. This folder — the template itself — is not a project, so if you run it here it will tell you so. - Easiest explanation first: Easy MCP Guide
- Client configs:
.mcp.json(Claude Code) · Cursor · Codex - Complete reference: docs/en/41-complete-mcp-reference.md
Note: GitMCP (free, remote) helps an AI read this public repo; the local sdd-mcp runs the real guided workflow. They complement each other: GitMCP guide.
Documentation
Browse online: the documentation site has every guide with search, an EN/ES language picker and level badges.
If you only read three:
- Workflow — the SDD flow step by step
- Structure — what each folder is for
- SDD in 2026: state of the art — the industry map and where this template stands
Everything else: the full documentation index organizes all 53 guides (EN/ES) by topic.
Community
- Docs site: juanklagos.github.io/spec-driven-development-template
- Questions, ideas, show-and-tell: GitHub Discussions
- Bugs and concrete proposals: Issues
- Interactive course: aprende-sdd — learn by doing, auto-graded by Actions
- Finished a tutor level?
/sdd:tutorrecords it in your logbook and hands you a completion badge for your README
Legal & authorship
- License: MIT — use it anywhere, including commercially and inside a company, free and without asking. Keep the copyright notice. Legal guide
- What you write with the templates is yours: TEMPLATE-OUTPUT.md
- Publishing a release / Publicar una versión: RELEASING.md
- Changelog: CHANGELOG.md · Latest release: v2.8.0
- Copyright (c) 2026 Juan Carlos Alvarez Lagos (AUTHORS.md)
<div align="center">
If this saves you one bad sprint, a ⭐ helps other people find it.
🌱 No code before approved spec and consistent plan.
</div>Related MCP servers
Premium Flutter UI components for AI coding agents. 46 widgets, 3 themes, light/dark mode.

Korean market data: kimchi premium, sell-side research, news. Pay per call in USDC via x402.
Korean equity research, analyst revisions, kimchi premium and news via x402.
Blocks typosquatted or hallucinated npm/PyPI packages before an AI agent installs them.

ARNO
The IDE for agents: read by symbol, edit against a revision, validate with your own build, revert.
