sense
Reduces debugging time and integration risk by giving AI agents precise codebase context—symbol relationships, change impact, and project patterns—instead of…
MCP server for AI coding agents - gives Claude Code, OpenCode, Cursor, and Codex CLI structural understanding of your codebase: symbol graph, blast radius, semantic search, conventions.
- Ask Claude to find all functions affected by changing a specific database schema field
- Generate a dependency map showing how microservices communicate before refactoring
- Automate code review by searching for places violating your project's naming conventions
Reduces debugging time and integration risk by giving AI agents precise codebase context—symbol relationships, change impact, and project patterns—instead of blind file searching.
Engineering teams using Claude or Cursor for code generation and refactoring who need AI agents to understand large, unfamiliar codebases.
https://github.com/luuuc/sense
By luuuc
How to Get It
claude plugins install luuuc/sense
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Find all functions affected by changing a specific database schema field
Trust Signals Auto-scanned
Community Pulse New
- AI agents write Ruby but can't navigate it: a 5-model, 13-codebase benchmark — Hacker News · 9 pts
- Sense, local code intelligence for AI coding agents — Hacker News · 2 pts
- Two of four code-Intel MCPs scored below grep in a benchmark I built — Hacker News · 1 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 25 GitHub stars; 3 contributors; last commit 0d 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): 25 GitHub stars; 3 contributors; last commit 0d ago; license MIT.