Best Tree Sitter AI Skills & MCP Servers

MCP server for RepoMap — code intelligence via AST-based repository analysis

A code indexing system accessible via MCP (Model Context Protocol)

MCP server that detects semantic (non-textual) merge conflicts between Git branches using AST-level analysis

Autonomous Repository Intelligence engine with web UI and MCP server. Unified semantic code understanding, local RAG, and agent working memory.

Deterministic QA plugin for Claude Code — CRAP index, Technical Debt Ratio, tree-sitter AST, SARIF 2.1.0, hooks, and a local Vue dashboard.

Model-agnostic code memory MCP server. Budget-aware graph retrieval for AI agents — sub-millisecond queries, token budgeting, no embeddings, no API keys. Built on CodeGraphContext for 155-language tree-sitter indexing.

Powerful MCP server with Tree-sitter WASM parsers for 100% AST accuracy. Zero native dependencies. Production-ready with persistent caching, structured logging, file watching, fuzzy search, rate limiting, file locking, and ReDoS protection. Supports TypeS

Multi-language tree-sitter parser — supports ~50 languages including TypeScript, Python, PHP, Go, Rust, HTML, YAML, JSON, Markdown, Twig, SCSS, etc.

Dependency graph + 23 MCP tools for AI coding assistants. Impact analysis, health scoring, security scanner, agent coordination.

RCA infrastructure for AI-built code. Code knowledge graph + opinionated RCA engine, exposed via MCP (Cursor / Claude Code / Cody / Cline / Continue / Windsurf / Zed) plus CLI and library. RCA is the wedge; the same engine covers code review, refactor bla

Code intelligence MCP server. Indexes your repository into a queryable call graph for AI coding agents.

Token-efficient source code navigation MCP server for AI agents