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.
Sandboxed bash for agents. Run untrusted commands in WebAssembly sandboxes with no setup required.
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
35/100 (Emerging)
44/100 (Fair)
Install path
Remote · high
npx · low
Engagement
2 0 0 15
1 0 0 6
Tools
Runs bash commands inside WebAssembly sandboxesProvides structured command output: stdout, stderr, exit code, and filesystem diffWorkspace directory mounted and isolated from host filesystemSupports custom commands and configurable initial working directoryPreload and reset sandbox state programmatically
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
