← All comparisons
Atelier vs code-index-mcp

What code-index-mcp says, vs. what it scored.

Tree-sitter AST indexing for 10 core languages, with fallback file indexing for 50+ more.

What code-index-mcp says about itself
“Intelligent code indexing and analysis for Large Language Models... bridges the gap between AI models and complex codebases.”
Publishes no numbers ...never against another search tool ~943 stars
What it actually scored — same 14 repos, same 7,213 queries as every other tool
Tool MRR p95 p100
Atelier +semantic (BGE) 0.727 390ms 1057ms
Atelier lexical (default) 0.676 134ms 319ms
code-index-mcp 0.343 377ms 3830ms

No performance or accuracy claim published in either direction -- no speed number, no quality number. On our benchmark it lands squarely mid-pack: 0.343 MRR, 377ms p95.

The true story

Every tool in this comparison, code-index-mcp included, has been through the exact same 14 repositories and 7,213 query/gold pairs that score Atelier — no cherry-picked queries, no separate corpus. Full methodology, every raw number, and the other 9 tools →