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.

DimensionShopify MCP ServerMCP server for Shopify Admin GraphQL API for AI assistantsMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS36 / 100 · D79 / 100 · B
Reliability5 / 2012 / 20
Security and permissions5 / 2018 / 20
Maintenance6 / 2016 / 20
Documentation11 / 2018 / 20
Setup experience9 / 2015 / 20
Best for
  • Developers who want to manage Shopify stores using AI assistants
  • Projects requiring programmatic access to the Shopify Admin API from MCP-compatible tools
  • Teams seeking a ready-made, production-grade Shopify MCP server
  • 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 don't need to manage a Shopify store or access the Admin API
  • Those seeking a server for the Shopify Storefront API (this server only uses the Admin API)
  • Users looking for an officially maintained MCP server (this one is not officially maintained by Shopify)
  • 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
  • Shopify Admin API access, requiring a custom app with Admin API scopes including `read_products`, `write_products`, `read_customers`, `write_customers`, `read_orders`, `write_orders` (plus scopes for inventory/metafields as needed)
  • Optional Redis connection for OAuth token persistence (if enabled)
  • Credentials via environment variables or CLI arguments (access token or client ID/secret)
  • 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
  • Credentials may be exposed: store client secrets or access tokens securely
  • Data loss or corruption risk due to write permissions (write operations are allowed)
  • Using a non-official server may introduce security or compatibility issues; review code at your own risk
  • Enabling Redis without proper configuration may cause startup failure or token cache issues
  • 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 clientsClaude DesktopClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools00