| FMRS | 29 / 100 · D | 79 / 100 · B |
|---|
| Reliability | 5 / 20 | 12 / 20 |
|---|
| Security and permissions | 5 / 20 | 18 / 20 |
|---|
| Maintenance | 6 / 20 | 16 / 20 |
|---|
| Documentation | 6 / 20 | 18 / 20 |
|---|
| Setup experience | 7 / 20 | 15 / 20 |
|---|
| Best for | - Users of AI coding tools (Claude, Cursor, etc.) who want to reduce token usage.
- Agents that need reliable, unambiguous Docker output for automated decision-making.
- Developers using Docker as part of their infrastructure and wanting MCP integration in their workflow.
| - 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 requiring interactive terminal control or full Docker CLI features (like attach, exec -it).
- Users unfamiliar with MCP configuration or Node.js environments.
- Users needing raw output from the Docker daemon, not structured data.
| - 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 | - Permissions to execute Docker commands, such as access to Docker socket or daemon (depending on environment).
- Network access for npx to download npm packages or Docker images (if pulling during builds).
- Filesystem access to read Dockerfiles or build contexts (if applicable).
| - 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 | - Running Docker commands may affect containers, images, or builds, e.g., removing containers or modifying images.
- Misconfiguration or network issues can cause Docker commands to fail, and agents may receive incomplete structured data.
- Using npx may introduce supply-chain risks, as remote code is downloaded and executed on each invocation.
| - 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, Claude Code, Cursor, VS Code, Windsurf, Cline, Roo Code, Codex, Gemini CLI, Zed, Continue | Claude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 5 | 0 |
|---|