by aimasteracc · MCP Server · ★ 42
🌳 Tree-sitter Analyzer English 简体中文 Code intelligence for AI agents: a pre-indexed, token-efficient MCP server — 8 MCP tools + CLI, 100% local. Instant structural answers. Who calls this? What would break? Generate a UML diagram. One call returns the whole answer — no grep loop. Token-budget aware. TOON output cuts bulk/tabular payload by 50-70% vs raw JSON (measured invariant); RFC-0012 measured 0.52× ratio on representative decision tools. Edit safely. + + constraint DSL gate every modification before it happens; ≈0 cross-language mis-wires in the call graph.
| Stars | 42 |
| Forks | 8 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 63.936620675297/100 |
| Open Issues | 1 |
| Last Updated | 2026-07-05 |
| Created | 2025-07-30 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~20k |
Explore other popular mcp server tools:
tree-sitter-analyzer is Cross-language-safe code-intelligence MCP for AI agents — 13 languages, family-gated call graph (CodeGraph wires 745 cross-language mis-wires on this repo, TSA 6 — ~390x cleaner). Run miswire-audit on. It is categorized as a MCP Server with 42 GitHub stars.
tree-sitter-analyzer is primarily written in Python. It covers topics such as ai, ai-agents, ai-coding.
You can find installation instructions and usage details in the tree-sitter-analyzer GitHub repository at github.com/aimasteracc/tree-sitter-analyzer. The project has 42 stars and 8 forks, indicating an active community.
tree-sitter-analyzer is released under the MIT license, making it free to use and modify according to the license terms.