██████╗ ██████╗ ███████╗ ██████╗██╗     ██╗███╗   ██╗████████╗███████╗██████╗
██╔════╝ ██╔══██╗██╔════╝██╔════╝██║     ██║████╗  ██║╚══██╔══╝██╔════╝██╔══██╗
███████╗ ██████╔╝█████╗  ██║     ██║     ██║██╔██╗ ██║   ██║   █████╗  ██████╔╝
╚════██║ ██╔═══╝ ██╔══╝  ██║     ██║     ██║██║╚██╗██║   ██║   ██╔══╝  ██╔══██╗
███████║ ██║     ███████╗╚██████╗███████╗██║██║ ╚████║   ██║   ███████╗██║  ██║
╚══════╝ ╚═╝     ╚══════╝ ╚═════╝╚══════╝╚═╝╚═╝  ╚═══╝   ╚═╝   ╚══════╝╚═╝  ╚═╝

    🔍 AI-Powered Specification Analysis  •  📊 Quality Grading  •  ⚡ Task Generation

git clone https://github.com/orangebread/speclinter-mcp.git
cd speclinter-mcp
pnpm install && pnpm build

{
  "mcpServers": {
    "speclinter": {
      "command": "node",
      "args": ["/absolute/path/to/speclinter-mcp/dist/cli.js", "serve"]
    }
  }
}

Given I have a vague specification: "Add social features"
When I ask SpecLinter to parse it
Then I get grade F with specific improvement suggestions
And actionable feedback like "Define specific social features"
And a template showing how to improve to grade A

Given I have a detailed spec: "Create user authentication with email verification, password reset, and 2FA"
When SpecLinter analyzes it
Then I get grade A with 8-12 structured tasks
And each task has acceptance criteria and Gherkin scenarios
And tasks are saved in organized directories

Given I've implemented my authentication feature
When I ask SpecLinter to validate it
Then AI scans my codebase for related files
And compares implementation against original spec
And provides quality score with specific recommendations

Given my teammate built user profile management
When I try to add "user settings page"
Then SpecLinter detects 85% similarity
And recommends extending existing feature
And prevents duplicate implementation

pnpm install && pnpm build

{
  "mcpServers": {
    "speclinter": {
      "command": "node",
      "args": ["/absolute/path/to/speclinter-mcp/dist/cli.js", "serve"]
    }
  }
}

# Test server starts
node dist/cli.js serve

# In your AI IDE, try:
"Initialize SpecLinter in my project"
"Parse this spec: Create a user login form"

{
  "mcpServers": {
    "speclinter-docs": {
      "command": "npx",
      "args": ["mcp-remote", "https://gitmcp.io/orangebread/speclinter-mcp"]
    }
  }
}

# Clone and build
git clone https://github.com/orangebread/speclinter-mcp.git
cd speclinter-mcp
docker build -t speclinter/mcp .

# Run SpecLinter server
docker run -d --name speclinter-server -v $(pwd):/workspace speclinter/mcp

{
  "mcpServers": {
    "speclinter": {
      "command": "docker",
      "args": ["exec", "-i", "speclinter-server", "node", "/app/dist/cli.js", "serve"]
    }
  }
}

"Add social features to the app"

As a user, I want to send direct messages to other users so that I can communicate privately.

Acceptance Criteria:
- Users can search for other users by username
- Messages are delivered in real-time using WebSocket
- Message history is preserved and searchable
- Users can block/unblock other users
- All messages are encrypted end-to-end

Error Handling:
- Show "User not found" for invalid usernames
- Display "Message failed to send" with retry option
- Handle offline users with message queuing

Feature: User Authentication System
  Implement secure user login and registration with email verification

  Scenario: Successfully authenticate user with valid credentials
    Given the user registration system is available
    And a user exists with email "user@example.com" and password "SecurePass123"
    When I submit login form with valid credentials
    Then the user should be authenticated successfully
    And a JWT token should be generated and returned
    And the user should be redirected to the dashboard
    And the login attempt should be logged

  Scenario: Handle invalid login attempts
    Given a user exists with email "user@example.com"
    When I submit login form with email "user@example.com" and password "WrongPassword"
    Then the authentication should be rejected
    And an error message "Invalid credentials" should be displayed
    And no JWT token should be generated
    And the failed attempt should be logged

  Scenario: Validate input format during login
    Given the login system is ready to accept input
    When I provide malformed email "invalid-email" and password "test123"
    Then input validation should be triggered
    And specific validation errors should be shown
    And the user should understand what needs to be corrected

Input: "user profile management"
Found: "user settings page" (85% similarity)
Recommendation: Extend existing feature

your-project/
├── .speclinter/
│   ├── config.json         # Settings
│   └── context/            # AI-generated project docs
└── speclinter-tasks/
    └── [feature-name]/
        ├── _active.md      # Status dashboard
        ├── task_*.md       # Individual tasks
        └── gherkin/        # Test scenarios

"Initialize SpecLinter in my project"
"Analyze my codebase to understand patterns and tech stack"

"Parse this spec: Create a user authentication system with email verification"
"Grade this specification: [your spec here]"
"Find similar features to: user profile management"
"Generate comprehensive Gherkin scenarios for my authentication feature"

"Show me the status of my authentication tasks"
"Mark the database setup task as completed"
"Validate the implementation of my login feature"
"Update task status for WebSocket connection to completed"

Create a product catalog page with filtering and search

As a user, I want to log in with email and password so I can access my account.

Acceptance Criteria:
- Email validation with proper error messages
- Password must be 8+ characters
- Failed attempts are rate-limited (3 attempts/5 minutes)
- Successful login redirects to dashboard
- Remember me option for 30 days

Scenario: Team coordination
  Given developer A built "user profile management"
  When developer B wants to add "user settings page"
  Then SpecLinter detects 85% similarity
  And recommends extending existing feature
  And prevents duplicate implementation

git clone https://github.com/orangebread/speclinter-mcp.git
cd speclinter-mcp

# Traditional development
pnpm install && pnpm build

# Available scripts
pnpm build        # Build for production
pnpm test         # Run Vitest tests (implementation validation)
pnpm lint         # Lint code with ESLint
pnpm dev          # Watch mode for development
pnpm start        # Start MCP server

# Docker development
docker build -t speclinter/mcp:latest .
docker run -it --rm -v $(pwd):/workspace speclinter/mcp