Structural codebase MCP server — navigate and edit code by symbol name, not raw text.
One MCP server. One profile. 97.9% on tsbench at -80% tokens. Structural code navigation, persistent memory, and Bash output compaction for AI coding agents. mibayy.github.io/token-savior -- project site + benchmark landing github.com/Mibayy/tsbench -- benchmark source + fixtures | Plain Claude Code | With Token Savior | Score | 141 / 180 (78.3%) | 188 / 192 (97.9%) | Active tokens / task | 17…
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Forge read 0 source files from the published package tarball and matched no MCP tool registrations. Extraction is pattern-based over shipped source: a server that builds its tool list at runtime, or that ships only bundled or minified code, registers nothing this can see. Treat it as “not detected”, not as “exposes none”.
One MCP server. One profile. 97.9% on tsbench at -80% tokens. Structural code navigation, persistent memory, and Bash output compaction for AI coding agents. mibayy.github.io/token-savior -- project site + benchmark landing github.com/Mibayy/tsbench -- benchmark source + fixtures | Plain Claude Code | With Token Savior | Score | 141 / 180 (78.3%) | 188 / 192 (97.9%) | Active tokens / task | 17 221 | 3 395 (-80%) | Wall time / task | 110.6 s | 18.9 s (-83%) | Reproduces with the profile (single…
Forge's dependency resolver reads npm metadata only, so this PyPI package has no resolved tree. That is a gap in coverage, not a clean bill of health.