Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
Answers "what did that command print?" from your real terminal history: a per-command PTY session recorder (OSC 133) stores every command's full output, exit code, cwd, and duration in local SQLite/FTS5, and the MCP server searches, retrieves, and diffs those outputs — secret redaction on by default before anything reaches the model.
Full-text search over your shell history (zsh / bash / fish) via SQLite FTS5. Local-only. 11-pattern secret redaction runs BEFORE insert. Captures cwd / exit code / duration via opt-in shell hook. Tools: searchhistory, recentindir, failedcommands, commandchains, reindex.
Quality signal
44/100 (Fair)
49/100 (Fair)
Install path
npx · low
npx · high
Engagement
1 0 0 6
1 0 0 4
Tools
Per-command PTY session recording with OSC 133 semantic-prompt marksLocal SQLite database with FTS5 trigram full-text searchZstd-compressed command outputs with configurable head/tail captureAutomatic redaction of secrets before output reaches the modelCross-platform shell integration for Bash, Zsh, Fish, PowerShellNo cloud or telemetry; all data stored locally in a single SQLite file
Full-text search with SQLite FTS5Local-only storage with secret redaction before insertOptional shell hook to capture cwd, exit code, and durationTools for searching, recent commands by directory, failed commands, and command chainsSupports zsh, bash, and fish shellsEasy integration with MCP clients via stdio
