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.

DimensionCoolify MCP ServerMCP server for managing self-hosted PaaS Coolify with 44 optimized tools.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS68 / 100 · C79 / 100 · B
Reliability10 / 2012 / 20
Security and permissions15 / 2018 / 20
Maintenance14 / 2016 / 20
Documentation15 / 2018 / 20
Setup experience14 / 2015 / 20
Best for
  • Developers and DevOps professionals using Coolify for self-hosted PaaS.
  • Teams looking to simplify daily deployment and operations with AI assistants.
  • Scenarios involving multiple Coolify instances.
  • 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 without a Coolify instance.
  • Operations that need fully automated destructive actions without confirmation (though you can disable confirmations with COOLIFY_MCP_ELICITATION=off).
  • Deployments to incompatible Coolify versions (only v4.0 and above supported).
  • 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
  • Requires a Coolify API access token (COOLIFY_ACCESS_TOKEN); its permissions determine what operations the MCP can perform.
  • Can read and modify resources such as apps, databases, services, and environment variables.
  • Destructive operations (e.g., delete, stop) trigger human confirmation unless disabled.
  • 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
  • If the API token has excessive permissions, unexpected deletion or stopping of resources could occur.
  • Destructive operations may cause data loss, but the confirmation mechanism reduces risk.
  • Sensitive information (like passwords and keys) is masked by default, but enabling reveal could pose a leak risk.
  • 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 Desktop, Claude Code, CursorClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools440