Show HN: Forensic-deepdive: code knowledge graph and MCP server for AI agents

This project provides a tool that converts a codebase into a structured knowledge graph (a map of files, classes, functions, and their relationships) and exposes it via an MCP (Model Context Protocol) server — a standard way for AI coding agents (like Claude, Copilot, or Cursor) to query that graph. Instead of an AI agent trying to parse raw code files line-by-line, it can use this graph to efficiently understand how code is organized, find relevant functions, or trace dependencies. This matters because current AI coding tools often struggle with large, unfamiliar codebases; a pre-built knowledge graph can make them dramatically faster and more accurate at navigation and reasoning. "Forensic" refers to analyzing the code structure in depth, similar to a forensic investigation.