The MCP server that turns Claude into the only coding agent hitting 100% on a real benchmark. -77% active tokens, -76% wall time, 0 losses across 96 tasks on Claude Opus 4.7. Structural code navigation + persistent memory. Works with every MCP client.
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…
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Forge read 1 source file from the repository archive 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…
This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.