| FMRS | 46 / 100 · D | 79 / 100 · B |
|---|
| Reliability | 7 / 20 | 12 / 20 |
|---|
| Security and permissions | 8 / 20 | 18 / 20 |
|---|
| Maintenance | 8 / 20 | 16 / 20 |
|---|
| Documentation | 11 / 20 | 18 / 20 |
|---|
| Setup experience | 12 / 20 | 15 / 20 |
|---|
| Best for | - Developers building websites or applications with AI coding tools
- Teams seeking design systems, interface prompts, and layout references
- AI users whose providers support markdown files or general prompting workflows
| - 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 who require a documented list of MCP tool names and parameters
- Users seeking traditional design software without an AI coding workflow
- Scenarios requiring authentication, permissions, or private-resource guarantees not documented in the source
| - 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 | - The client needs access to the remote MCP endpoint at https://mcp.typeui.sh/mcp
- Local CLI workflows require installing dependencies and writing generated SKILL.md or DESIGN.md files
- The source does not specify authentication requirements for the remote server
| - 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 | - The server manifest does not enumerate MCP tools, so its callable capabilities cannot be confirmed from the source
- No authentication or data-handling details are provided
- Generated design guidance still requires human review against project requirements and UI/UX fundamentals
- The Pro version includes enhanced design skills, layout prompts, and a private Discord community, so some resources may not be public
| - 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 | Codex, Claude, Cursor, Grok, Z.ai, Hermes, OpenClaw, Eve, Mistral, OpenCode, VS Code, Antigravity, Windsurf, JetBrains IDEs, Zed, GitHub Copilot, Cline, Qwen, Amp, Goose | Claude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 0 | 0 |
|---|