Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for AI coding-agent teams, code-intelligence builders, and platform engineers who need a correct cross-language call graph behind MCP, because TSA ships an MIT-licensed Python MCP server with 8 tools, tree-sitter indexing across 13 languages, TOON output (~half the size of JSON), and curated Skills on top of Claude Code / Cursor support, which means a coding agent can answer 'where is this
Who should use it
Who should skip it
Skip if the source link, docs, or setup requirements do not match your workflow.
Risk explanation
It indexes source code on the local machine via tree-sitter and exposes the results to AI agents, so confirm the project root boundary before pointing it at a private repo, audit which Skills are enabled, and lock down which call-graph outputs are persisted.