M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionStitch MCPSeamlessly bring AI-generated UI designs from Google's Stitch into your development workflow.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS46 / 100 · D79 / 100 · B
Reliability6 / 2012 / 20
Security and permissions8 / 2018 / 20
Maintenance8 / 2016 / 20
Documentation13 / 2018 / 20
Setup experience11 / 2015 / 20
Best for
  • Designers and developers who want to integrate AI-generated UI designs into their development workflow.
  • Teams that want to use coding agents to quickly generate code based on designs.
  • Developers using MCP-supported IDEs like VS Code, Cursor, etc.
  • 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
  • People who do not use Google Stitch or do not need integration with it.
  • Those seeking an officially supported Google solution (this tool is an independent experimental project).
  • Users who need a graphical interface for browsing designs (primarily CLI-based).
  • 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
  • Access to Google Cloud project and enable Stitch API.
  • Run a Vite development server locally and build Astro projects.
  • Access terminal and file system to generate project files.
  • 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
  • Experimental project, may not be maintained, or incompatible with future Stitch API versions.
  • Requires valid Google Cloud credentials; misconfiguration may lead to permission errors.
  • In headless environments (e.g., SSH, Docker), browser-based authentication may not work automatically; you need to manually copy the OAuth URL.
  • 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 clientsVS Code, Cursor, Claude Code, Gemini CLI, Codex, OpenCodeClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools30