Code Audit (Ollama)

Provides local code auditing using Ollama models to analyze security vulnerabilities, performance bottlenecks, quality issues, architectural problems, testing gaps, and documentation deficiencies across multiple programming languages with configurable analysis depth and severity classification.

This MCP server provides AI-powered code auditing capabilities using local Ollama models to analyze code for security vulnerabilities, performance bottlenecks, quality issues, architectural problems, testing gaps, documentation deficiencies, and implementation completeness. Built by Warren Gates using TypeScript with the Model Context Protocol SDK, it features specialized auditors for each analysis type, configurable model selection strategies, complexity analysis utilities, and a comprehensive CLI tool for setup, health checking, and server management. The implementation supports multiple audit modes (fast/thorough), language-specific analysis patterns, severity-based issue classification, and both stdio and HTTP transport modes, making it valuable for code review workflows, continuous integration pipelines, and building AI assistants that need programmatic access to detailed code quality analysis without relying on external services.