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.

DimensionCloudflare MCP ServerToken-efficient access to the Cloudflare API.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS49 / 100 · D79 / 100 · B
Reliability8 / 2012 / 20
Security and permissions7 / 2018 / 20
Maintenance8 / 2016 / 20
Documentation13 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • Developers and operators managing Cloudflare resources through an agent.
  • Users who need access to many Cloudflare API endpoints with low context usage.
  • CI/CD and automation 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 do not use the Cloudflare API.
  • Users who require a locally run stdio server.
  • Users unable to grant the required Cloudflare permissions.
  • 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
  • OAuth connections require Cloudflare authorization and selected permissions.
  • API Tokens must include the Cloudflare permissions required for the intended operations.
  • Account Tokens need Account Resources : Read to allow automatic account ID detection.
  • 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
  • A Token with write permissions can create or modify Cloudflare resources through API operations.
  • Disabling Code Mode registers about 2,500 API endpoints as individual tools and substantially increases token cost.
  • API Tokens with Client IP Address Filtering enabled are currently unsupported.
  • An incorrect account ID or insufficient permissions can cause requests to fail or target the wrong account.
  • 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
Tools30