| FMRS | 54 / 100 · D | 79 / 100 · B |
|---|
| Reliability | 7 / 20 | 12 / 20 |
|---|
| Security and permissions | 6 / 20 | 18 / 20 |
|---|
| Maintenance | 12 / 20 | 16 / 20 |
|---|
| Documentation | 15 / 20 | 18 / 20 |
|---|
| Setup experience | 14 / 20 | 15 / 20 |
|---|
| Best for | - Developers who want AI assistants to directly control terminal and file system.
- Users who need enhanced code editing, automation, and codebase exploration within MCP clients like Claude Desktop.
- Scenarios requiring handling of complex file formats like Excel, PDF, DOCX.
| - Engineering teams scaling AI coding agents while controlling spend
- Platform teams that need auditable, rollback-aware agent execution records
- Organizations using multiple agents (Claude, Codex, Gemini) under one governed flow
|
|---|
| Not for | - Users needing a fully sandboxed environment (unless using Docker installation).
- Security-sensitive environments, as terminal commands can bypass directory restrictions.
- Users who don't need terminal control and only basic file operations.
| - Developers who just want a simple code-completion helper without run governance
- Teams unwilling to accept local JSONL run records with HMAC signing
- Environments without a supported adapter (Claude/Codex/Gemini CLIs, direct provider, or verifier-only)
|
|---|
| Required permissions | - Filesystem read/write permissions, including terminal commands that can access files outside allowedDirectories.
- Ability to execute arbitrary terminal commands (subject to blockedCommands).
- Manage processes (start, interact, terminate).
- Access network to fetch URL content (read_file).
| - Read/write access to the configured repo root (writable scope restrictable via --allow-path/--deny-path)
- Ability to invoke the chosen agent CLI (Claude/Codex/Gemini, etc.) and its underlying model account
- Local disk writes for run records, receipts, and share outputs (share/run-receipt., etc.)
- Execution of user-configured verifier commands (e.g. npm test)
|
|---|
| Risks and side effects | - Terminal commands can access files outside allowedDirectories, posing a security risk.
- Command blocklist may be bypassed via symlinks, command substitution, or absolute paths.
- Configuration changes should be made in a separate chat window to avoid accidental modification by Claude.
- Potential risk to host system if not using Docker isolation.
| - Verifier commands are executed; poorly chosen verifier commands carry security risk despite preflight policy checks
- Cost and token figures may be estimates (labeled with provenance) and should not be treated as settled accounting
- Receipt integrity must be verified before use as trustworthy evidence; missing rollback evidence is flagged as EVIDENCE_BOUNDARY
- Policy defaults come from martin.config.yaml and can be overridden by CLI flags; misconfiguration can loosen safety boundaries
|
|---|
| Supported clients | Claude Desktop, Cursor, Windsurf, VS Code / GitHub Copilot, Cline, Roo Code, Claude Code, Trae, Kiro, Codex, JetBrains IDEs, Gemini CLI, Augment Code, Qwen Code | Claude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 25 | 0 |
|---|