A microservice catalog test found Markdown, GraphRAG, and MCP graphs fail in different ways
JeremyCMorgan · x · 2026-07-29
The post compares three knowledge-base approaches for a microservice catalog: plain Markdown, GraphRAG, and exact graph tools exposed through MCP.
The key finding is about failure modes:
- Markdown missed actual consumers.
- GraphRAG pulled in unrelated neighboring information.
- Graph tools computed dependencies deterministically.
The takeaway is that the strongest signal is not which method sounds best, but which failure shape each method produces.
More from coding & agent
- Relume MCP and Claude Code power a Markdown-first design workflow — michalmalewicz · 2026-07-29
- A research talk compares SWE-bench, CodeClash, and ProgramBench for agentic coding — OfirPress · 2026-07-29
- Kuna debuts as an agent-driven Rust decompiler, ranking near Hex-Rays in structuring — moyix · 2026-07-29
- $100k Bet: AI 'Vibecoding' Can't Match Complex SEO Tools Like Ahrefs — eptwts · 2026-07-29
- An AI-agent startup argues billing should work from facts, not scattered API calls — davidcrawshaw · 2026-07-29
- Most Cursor users still treat it like VS Code, despite 1M users and a $29.3B valuation — nikola_mr64990 · 2026-07-29