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.
Stateful, structured, auditable shell sessions for AI agents over local, SSH, and Docker. Secret redaction, output budgeting, SSH host-key verification, and a loopback read-only browser viewer that streams the live transcript.
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.
Quality signal
44/100 (Fair)
44/100 (Fair)
Install path
pip · high
npx · low
Engagement
3 0 0 7
1 0 0 6
Tools
Persistent sessions with stateful working directory and environmentStructured ExecResult with stdout, stderr, exit code, duration, and cwdPolicy fence to allow or deny commands before executionSecret redaction and output size bounding to prevent data leaks and floodingSupport for local, SSH, and Docker transports with uniform APISession checkpoint and restore for undoing remote workspace changes
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
