I built an MCP server that forces AI to spec before it codes

Source: Dev.to

I built an MCP server that forces AI to spec before it codes

I built an MCP server in Go that gives your AI persistent memory, structured specifications, and an adaptive change pipeline. It’s called Hoofy. It’s open source. Its only reason to exist is to make your AI build what you want, not what it hallucinates.

The Problem Nobody Wants to Admit

We’re all using AI to code, and we face the same issues:

• Ask for a feature → get something that looks right but isn’t
• New session → AI has no idea what you did yesterday
• “Fix this bug” → AI rewrites half your codebase
• Complex request → invented APIs, mismatched schemas, architecture that contradicts your existing code

The METR 2025 study confirmed it with data: experienced developers were 19 % slower with AI, despite feeling 20 % faster. DORA 2025 found a 7.2 % increase in delivery instability for every 25 % of AI adoption without structure. McKinsey says only those using structured specifications see real improvements (16‑30 %).

AI without structure is a junior with blind confidence.

What is Hoofy

Hoofy is an MCP server — a single binary written in Go, with zero external dependencies and an embedded SQLite database. Connect it to any AI tool that supports MCP (Claude Code, Cursor, VS Code Copilot, OpenCode, Gemini CLI) and it gives your AI three superpowers:

Persistent Memory (17 tools)

Your AI finally remembers. Architecture decisions, bugs you fixed, patterns you established, technical discoveries—everything is saved in SQLite with full‑text search (FTS5) and a knowledge graph with typed relations. When a new session starts, Hoofy loads this context automatically, so the AI already knows where it left off.

Adaptive Change Pipeline (6 tools)

When you need to make a change, Hoofy automatically selects the right steps based on type × size:

All 12 flows are deterministic. A small bug‑fix doesn’t need the same ceremony as a new authentication system, but all flows start with a context‑check—Hoofy scans existing specs, completed changes, memory, and convention files to detect conflicts before writing a single line.

Greenfield Project Pipeline (9 tools)

For brand‑new projects, Hoofy provides a full pipeline:

Init → Propose → Requirements → Business Rules → Clarity Gate → Design → Tasks → Validate

• Clarity Gate: Analyzes requirements across eight dimensions (users, functionality, data model, integrations, edge cases, security, scale, scope) and blocks advancement until ambiguities are resolved.
• Business Rules: Extracts declarative rules using the BRG taxonomy (Definitions, Facts, Constraints, Derivations) and DDD Ubiquitous Language before the Clarity Gate evaluates them.
• Validate: Cross‑checks all artifacts—every requirement has at least one task, every design component has assigned tasks, and nothing falls outside the proposal’s scope.

What Hoofy Is Not

• It doesn’t generate code. Hoofy generates specifications; the AI generates code after using those specs as guardrails.
• It doesn’t replace the developer. You still make the decisions; Hoofy forces the AI to ask you before assuming.
• It isn’t exclusive to one tool. It follows the standard MCP protocol and works with any IDE or tool that supports it.

The Research Behind It

Hoofy is grounded in established standards and research:

• IEEE 29148 and IREB – Requirements engineering standards for structured elicitation and ambiguity detection.
• Business Rules Group (BRG) – The Business Rules Manifesto establishes rules as first‑class citizens, not buried in code.
• EARS (Easy Approach to Requirements Syntax) – Templates that eliminate ambiguity in natural‑language requirements.
• DDD Ubiquitous Language – Eric Evans’ principle that a shared language eliminates translation errors.

A requirements error costs 10‑100× more to fix in production than during specification (IEEE). With AI‑generated code, that multiplier worsens.

Quick Start

Install

# macOS (Homebrew)
brew install HendryAvila/hoofy/hoofy

# macOS/Linux (script)
curl -sSL https://raw.githubusercontent.com/HendryAvila/Hoofy/main/install.sh | bash

# Go
go install github.com/HendryAvila/Hoofy/cmd/hoofy@latest

Connect (example with Claude Code)

claude mcp add --scope user hoofy hoofy serve

Now just talk to your AI. Hoofy’s built‑in instructions tell it when and how to use each system.

By the Numbers

• 32 tools support MCP
• 12 flow variants in the change pipeline
• 8 dimensions of clarity
• 6 relation types in the knowledge graph
• One binary, zero external dependencies, MIT license

GitHub:

Stop prompting. Start specifying.