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.

DimensionIntlayer MCP ServerAI-powered i18n and content management for development environmentsMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS31 / 100 · D79 / 100 · B
Reliability2 / 2012 / 20
Security and permissions8 / 2018 / 20
Maintenance11 / 2016 / 20
Documentation7 / 2018 / 20
Setup experience3 / 2015 / 20
Best for
  • Developers building web or mobile applications with JavaScript or TypeScript
  • Teams needing internationalization for Next.js, React, Vite, or React Native
  • Projects seeking AI translation, CMS capabilities, and visual editing
  • 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 seeking generic browser, database, or cloud-storage operations
  • Users requiring documented transport, authentication, or tool details
  • Projects without internationalization or multilingual content-management needs
  • 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 source does not state which file, network, account, or API permissions the server requires.
  • AI translation can use the user's own AI provider or API key, but the source does not explain how the MCP server accesses or uses those credentials.
  • 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
  • Transport, authentication, deployment, and access-control details are not documented in the source, so the operational security boundary cannot be confirmed.
  • AI-generated translations may require human review; the source states that AI translation is supported but provides no quality guarantee.
  • Externalizing content to the CMS may change how content is synchronized with Git.
  • 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 Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools00