Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AI_MODEL | No | AI model to use for execution | anthropic/claude-3-sonnet |
| LOG_LEVEL | No | Logging level (DEBUG, INFO, WARN, ERROR) | |
| AI_TIMEOUT | No | Request timeout in ms | 60000 |
| PROJECT_PATH | Yes | Path to the project directory to analyze | |
| ADR_DIRECTORY | No | Directory containing ADR files | docs/adrs |
| AI_MAX_TOKENS | No | Response length limit | 4000 |
| AI_TEMPERATURE | No | Response consistency (0-1) | 0.1 |
| EXECUTION_MODE | No | Execution mode: 'full' (AI execution) or 'prompt-only' (legacy) | prompt-only |
| AI_CACHE_ENABLED | No | Enable response caching | true |
| OPENROUTER_API_KEY | No | OpenRouter API key from https://openrouter.ai/keys (Required for AI execution) |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| goal_specification | Specify project goals and requirements for comprehensive analysis |
| action_confirmation | Confirm actions before writing files to disk |
| ambiguity_resolution | Resolve ambiguities in project analysis or requirements |
| custom_rule_definition | Define custom architectural rules and validation criteria |
| baseline_analysis | Generate comprehensive baseline analysis for existing projects |
| secret_prevention_guidance | Proactive guidance to prevent secret exposure in code and documentation |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Architectural Knowledge Graph | Complete architectural knowledge graph of the project |
| Analysis Report | Comprehensive project analysis report |
| ADR List | List of all Architectural Decision Records |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_project_ecosystem | Comprehensive recursive project ecosystem analysis with advanced prompting techniques (Knowledge Generation + Reflexion) |
| get_architectural_context | Get detailed architectural context for specific files or the entire project, automatically sets up ADR infrastructure if missing, and provides outcome-focused workflow for project success |
| generate_adrs_from_prd | Generate Architectural Decision Records from a Product Requirements Document with advanced prompting techniques (APE + Knowledge Generation) |
| generate_adr_todo | Generate TDD-focused todo.md from existing ADRs with JSON-first approach: creates structured JSON TODO and syncs to markdown |
| compare_adr_progress | Compare TODO.md progress against ADRs and current environment to validate implementation status |
| analyze_content_security | Analyze content for sensitive information using AI-powered detection |
| generate_content_masking | Generate masking instructions for detected sensitive content |
| configure_custom_patterns | Configure custom sensitive patterns for a project |
| apply_basic_content_masking | Apply basic content masking (fallback when AI is not available) |
| validate_content_masking | Validate that content masking was applied correctly |
| manage_cache | Manage MCP resource cache (clear, stats, cleanup) |
| configure_output_masking | Configure content masking for all MCP outputs |
| suggest_adrs | Suggest architectural decisions with advanced prompting techniques (Knowledge Generation + Reflexion) |
| generate_adr_from_decision | Generate a complete ADR from decision data |
| discover_existing_adrs | Discover and catalog existing ADRs in the project |
| incorporate_research | Incorporate research findings into architectural decisions |
| create_research_template | Create a research template file for documenting findings |
| request_action_confirmation | Request confirmation before applying research-based changes |
| generate_rules | Generate architectural rules from ADRs and code patterns |
| validate_rules | Validate code against architectural rules |
| create_rule_set | Create machine-readable rule set in JSON/YAML format |
| analyze_environment | Analyze environment context and provide optimization recommendations |
| generate_research_questions | Generate context-aware research questions and create research tracking system |
| analyze_deployment_progress | Analyze deployment progress and verify completion with outcome rules |
| check_ai_execution_status | Check AI execution configuration and status for debugging prompt-only mode issues |
| get_workflow_guidance | Get intelligent workflow guidance and tool recommendations based on your goals and project context to achieve expected outcomes efficiently |
| get_development_guidance | Get comprehensive development guidance that translates architectural decisions and workflow recommendations into specific coding tasks, implementation patterns, and development roadmap |
| read_file | Read contents of a file |
| write_file | Write content to a file |
| list_directory | List contents of a directory |
| manage_todo_json | JSON-first TODO management with consistent LLM interactions, automatic scoring sync, and knowledge graph integration |
| generate_deployment_guidance | Generate deployment guidance and instructions from ADRs with environment-specific configurations |
| smart_git_push | AI-driven security-focused git push with credential detection, file filtering, and deployment metrics tracking. Tests should be run by calling AI and results provided. |
| deployment_readiness | Comprehensive deployment readiness validation with test failure tracking, deployment history analysis, and hard blocking for unsafe deployments. Integrates with smart_git_push for deployment gating. |
| troubleshoot_guided_workflow | Structured failure analysis and test plan generation - provide JSON failure info to get specific test commands |
| smart_score | Central coordination for project health scoring system - recalculate, sync, diagnose, optimize, and reset scores across all MCP tools |