#code-intelligence

AI-powered code search MCP server using Exa API for intelligent code search and retrieval in AI assistants

CodeConductor IDE Orchestrator gives Claude Desktop full access to your development environment through a secure MCP server. It connects Claude to your VS Code workspace, enabling real file operations, code navigation, Git workflows, and automated development tasks. The server exposes 24 IDE tools, including: File operations — open, read, write, list, search Code intelligence — go to definition, find references, diagnostics Git automation — status, diff, stage, commit, push (Pro) Command execution — run terminal commands safely (Pro) Command Execution Safety: Pro users can run commands through Claude, but everything is protected by a three-tier safety system. Safe commands run automatically, while higher-risk commands require explicit confirmation and are screened for dangerous patterns. This prevents accidental damage and blocks command injection attempts. All operations run locally on your machine, never transmit code, and follow a tier-based permission system (Free vs Pro). Requires the CodeConductor VS Code extension to function. This orchestrator turns Claude into a capable, controlled development assistant that operates directly inside your real project.

The semantic layer for software engineering: Connect code to meaning, build on understanding

Cursor AI SSOT & Rule Engine Template: A comprehensive framework for integrating Cursor AI's advanced features into any project. Includes Single Source of Truth (SSOT) tracking, custom project rules, and Model Context Protocol (MCP) with Knowledge Graph for intelligent context management.

Local-first MCP code intelligence server with 37 tools — hybrid search, blast-radius analysis, diff-aware risk-scored review, and bi-temporal memory pinned to git SHAs. Stops AI agents from hallucinating function names that don't exist in your codebase. Published 60-task retrieval benchmark with reproducible harness. MIT.

Save tokens while coding — your AI agent gets structured code context, not file dumps. CodeWeave is an MCP server that gives AI agents structured code intelligence instead of dumping entire files into context. Your agent queries local indexes — AST, call graph, type graph, and hybrid semantic search — and gets back only what it needs. The result: less token waste, more relevant context, better coding decisions. It supports 7 languages (Python, TypeScript, JavaScript, Go, Rust, Java, C#) with a 6-stage hybrid search pipeline combining vector embeddings, full-text search, and structural density scoring. Everything runs locally with zero external dependencies beyond Ollama for embeddings. Monorepo and git worktree support included. A file watcher keeps indexes current as code changes — no manual reindexing needed. ATTENTION: Run "npx @codeweave/mcp" in your project directory first. The setup wizard handles everything for you. At first, it may take some time. INFO: Exhaustively tested on large Java, C#, JavaScript, TypeScript, React codebases. Contributions and feedback are welcome.