High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
MCP server for spec-driven development prompts
This MCP server gives your agent a three-step path from requirements to design to code. It uses structured prompts, including EARS-style requirements, and stores outputs in `specs/requirements.md` and `specs/design.md` before generating implementation code.
Builders who want their agent to work from requirements and design instead of jumping straight to code.
You can move from vague ideas to traceable specs and implementation in a repeatable order.
What it does
Requirements generation
Creates a `requirements.md` document from a high-level app idea using EARS format.
Design generation
Reads `specs/requirements.md` and produces `specs/design.md`.
Code generation
Reads `specs/design.md` and generates implementation code in the project root.
MCP integration
Works through MCP so it can be attached to compatible tools like VS Code, Cursor, and Claude Code.
README
Spec-Driven Development MCP Server
Model Context Protocol (MCP) server that facilitates spec-driven development workflows by providing structured prompts for generating requirements, design documents, and code following a systematic approach.
🎯 Purpose
This MCP server enables developers to follow a structured spec-driven development approach by providing prompts that guide you through:
- Requirements Generation - Create detailed requirements documents using the EARS (Easy Approach to Requirements Syntax) format
- Design Generation - Generate design documents based on requirements
- Code Generation - Generate implementation code based on design documents
✨ Features
- Structured Workflow: Follows a clear progression from requirements → design → code
- EARS Format Support: Uses industry-standard EARS format for requirements documentation
- MCP Protocol: Integrates seamlessly with MCP-compatible tools and environments
🚀 Quick Start
Prerequisites
- Node.js 20+
Installation
VS Code
Install the MCP server in VS Code using below buttons:
Alternatively, you can add configuration in mcp.json:
{
"servers": {
"spec-driven": {
"command": "npx",
"args": [
"-y",
"mcp-server-spec-driven-development@latest"
]
}
}
}
Cursor, Claude Code
Install the MCP server in Cursor using below button:
Alternatively, you can add configuration in mcp.json:
{
"mcpServers": {
"spec-driven": {
"command": "npx",
"args": [
"-y",
"mcp-server-spec-driven-development@latest"
]
}
}
}
📋 Available Prompts
1. Generate Requirements Document
- Name:
generate-requirements - Description: Generate requirements.md using EARS format
- Input: High-level requirements of the application. Example: 'A Vue.js todo application with task creation, completion tracking, and local storage persistence'
- Output: Structured requirements document in
specs/requirements.md
2. Generate Design from Requirements
- Name:
generate-design-from-requirements - Description: Generate design.md from requirements.md
- Input: Reads from
specs/requirements.md - Output: Design document in
specs/design.md
3. Generate Code from Design
- Name:
generate-code-from-design - Description: Generate code from design.md
- Input: Reads from
specs/design.md - Output: Implementation code in the root folder
📖 Workflow Example
- Start with Requirements: Use the
generate-requirementsprompt with your initial requirements text - Create Design: Use
generate-design-from-requirementsto create a design document based on your requirements - Generate Code: Use
generate-code-from-designto generate implementation code from your design
This creates a traceable path from requirements through design to implementation, ensuring consistency and completeness in your development process.
🤔 Why Spec-Driven Development?
Moving beyond Vibe Coding to a structured, specification-driven approach brings clarity, consistency, and maintainability to your development workflow. Instead of coding by intuition alone, Spec-Driven Development provides a systematic foundation that scales with your project's complexity.
Learn more about the benefits: Goodbye, Vibe Coding! Hello, Spec-Driven Development MCP Server!
Files in the repo
- .vscode
- src
- .gitignore
- LICENSE
- package-lock.json
- package.json
- README.md
- server.json
- tsconfig.json
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
20 MB lightweight cross-platform database client for 90+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker. | 轻量级跨平台数据库管理工具,支持 MySQL、PostgreSQL、SQLite、Redis、MongoDB、达梦等 90+ 数据库,提供桌面端、Docker、CLI、内置 AI 助手和 MCP Server。