Graph-It-Live
Answers 'what breaks if I touch this?' with one-click reverse dependency lookup, auto-detects circular dependencies, and gives AI assistants a 22-tool MCP se…
VS Code extension that turns a codebase into a live, interactive dependency graph across three layers: file-to-file imports, symbol-level call hierarchy (AST via ts-morph), and a cross-file live call graph (Tree-sitter + SQLite). Exposes all three layers to AI assistants through a 22-tool MCP server, plus a standalone CLI and an agent skill.
- Look up reverse dependencies to see what breaks before touching a file
- Auto-detect and highlight circular dependencies in the file graph
- Let your AI assistant query call graphs and generate codemaps through the 22-tool MCP server
Answers 'what breaks if I touch this?' with one-click reverse dependency lookup, auto-detects circular dependencies, and gives AI assistants a 22-tool MCP server so architecture questions are answered from a real code graph instead of grep and guesswork.
Backend engineers and full-stack developers working with complex algorithms or data transformations requiring immediate visual feedback.
https://github.com/magic5644/Graph-It-Live
By magic5644
How to Get It
Install 'Graph-It-Live' from the VS Code Marketplace or Open VSX (magic5644.graph-it-live); CLI available via npm as @magic5644/graph-it-live
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me look up reverse dependencies to see what breaks before touching a file
Trust Signals Auto-scanned
Community Pulse Quiet
No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 34 GitHub stars; contributors unknown; last commit 1d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 34 GitHub stars; contributors unknown; last commit 1d ago; license MIT.