codebase-memory-mcp vs jCodeMunch MCP
Both are code understanding MCP servers, and we ran both through the same test (find definition) in each app. codebase-memory-mcp passed 4 of 4 apps we tested it in; jCodeMunch MCP passed 4 of 4.
Test results side by side
| codebase-memory-mcp | jCodeMunch MCP | |
|---|---|---|
| Claude Code | Passed 2026-10-20 | Passed 2026-10-22 |
| Cursor | Passed 2026-10-20 | Passed 2026-10-22 |
| Claude Desktop | Passed 2026-10-14 | Passed 2026-10-22 |
| ChatGPT (Codex) | Passed 2026-10-14 | Passed 2026-10-22 |
| Tools exposed (protocol check) | 17 tools | 6 tools |
| GitHub stars | 46,592 | 2,789 |
| License | MIT | NOASSERTION |
| Last push | 2026-10-14 | 2026-10-20 |
Results from our own harness runs, dated per cell. Stars and last push from GitHub at our last data refresh. We don’t pick a winner here: which one fits depends on your app and setup.
What each does
codebase-memory-mcp: Indexes a codebase into a persistent knowledge graph your agent can query, shipped as a single static binary with no dependencies.
jCodeMunch MCP: Retrieves code by symbol (functions, classes) using tree-sitter parsing, so agents read only what they need from a repo instead of whole files.
