Back to browse
GitHub Repository

AI bug finder and code analyzer

19 starsJavaScript

An MCP server that fact-checks AI bug diagnoses against AST evidence

by EruditeCoder108·Apr 22, 2026·3 points·1 comment

AI Analysis

●●●BangerBig BrainSolve My Problem

Forces LLMs to debug with AST evidence instead of pattern-matching symptoms.

Strengths
  • Tree-Sitter AST parsing extracts verified structural facts before AI guesses
  • Semantic archive stores past diagnoses so similar bugs get archive hits first
  • Works with Claude Code, Gemini CLI, Cursor, and any MCP-compatible agent
Weaknesses
  • Only 13 stars and BSL1.1 license may limit community contribution
  • JavaScript/TypeScript only—no Python or Rust AST support yet
Category
Target Audience

Developers using AI coding assistants for debugging

Similar To

Cursor · Continue · Sourcegraph Cody

Similar Projects

AI/ML●●●Banger

Director-AI – token-level NLI+RAG

Token-level streaming halt stops hallucinations mid-sentence before user sees them—genuinely novel safety layer.

Big BrainWizardry
anulum
273mo ago
Security●●Solid

Fix MCP OAuth Gaps (CLI and CI Check)

The project maps the entire OAuth/MCP discovery-to-DCR funnel and gives actionable failure points — e.g., missing WWW-Authenticate headers, malformed PRM or issuer metadata, or broken token endpoints. It’s a focused, practical CLI that also fits into CI (GitHub Actions badge, quickscan command), so teams can catch auth regressions before rollout. Niche but very useful if you run or validate MCP/OAuth endpoints; wider adoption will depend on more examples and integration templates.

Niche GemSolve My Problem
chintant
213mo ago
Developer Tools●●Solid

Code Scalpel – AST analyzer and security scanner (MCP server)

It turns real program analysis — ASTs, cross-file dependency graphs, taint tracking and Z3 symbolic paths — into callable MCP tools for agents, not just another prettier linter. Concrete features like simulate_refactor, generate_unit_tests from symbolic paths, and cross-file security_scan give it a distinct technical voice. The <10% false-positive claim and heavy test coverage are promising, but I'd want to see results on large, messy repos before swapping out existing scanners.

WizardryNiche Gem
digitalbyooki
203mo ago