No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by aimasteracc · MCP Server · ★ 50
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is tree-sitter-analyzer safe to install? View the security audit →
🌳 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. 100% local means the index lives in inside your repo, no telemetry, no remote calls. Every MCP response + CLI output is generated locally from the SQLite+FTS5 cache. Upgrading from v1.x? See docs/MIGRATION.md. [ claude plugin marketplace
Roslyn-based MCP server giving AI agents deep semantic understanding of .NET/C# codebases — 67 tools for navig
📜 An MCP server for conversation history search and retrieval in Claude Code
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, blast radius, health grading, 8 facade tools, JSON envelopes, 100% local. Run miswire-audit on your repo. It is categorized as a MCP Server with 50 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 50 stars and 12 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.
The top alternatives to tree-sitter-analyzer on Agent Skills Hub include fossil-mcp, compass, cli. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: