mcp-adr-analysis-server
by tosin2013
Overview
AI-powered Architectural Decision Record (ADR) analysis, generation, and validation server. It integrates advanced prompting techniques (GKP, APE, Reflexion) to assist with software architecture, development workflows, deployment, security analysis, rule generation, and project planning.
Installation
node dist/src/index.jsEnvironment Variables
- OPENROUTER_API_KEY
- AI_MODEL
- PROJECT_PATH
- ADR_DIRECTORY
- LOG_LEVEL
- AI_BASE_URL
- AI_SITE_URL
- AI_SITE_NAME
- EXECUTION_MODE
- TS_PARSER_DIR
- USER
Security Notes
The server uses `child_process.execSync` and `child_process.exec` extensively (e.g., for git operations, npm commands, gitleaks, kubectl/oc/docker commands, shell scripts from ADRs/patterns). This pattern is highly susceptible to command injection vulnerabilities if AI-generated or user-provided inputs are not perfectly sanitized. It also creates and runs temporary files from content for Tree-sitter analysis, which can be risky if malicious content is processed. Direct execution of arbitrary shell commands within a server process is a critical security risk.
Similar Servers
code-index-mcp
Provides intelligent code indexing, searching, and analysis capabilities for large language models to understand and navigate codebases.
CodeGraphContext
An MCP server that indexes local code into a Neo4j graph database to provide real-time, accurate context and relationship analysis to AI assistants for understanding, writing, and refactoring code.
In-Memoria
Provides persistent intelligence infrastructure (semantic concepts, patterns, architecture) for AI agents to understand and interact with codebases.
conductor-tasks
Conductor Tasks is an intelligent assistant for developers, transforming requirements into actionable tasks, generating implementation plans, tracking progress, and accelerating AI-powered development directly within the workflow. It serves as a comprehensive AI co-pilot for the development process.