← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

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

DimensionkubefwdBulk Kubernetes service forwarding for local development.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS34 / 100 · D79 / 100 · B
Reliability2 / 2012 / 20
Security and permissions6 / 2018 / 20
Maintenance9 / 2016 / 20
Documentation10 / 2018 / 20
Setup experience7 / 2015 / 20
Best for
  • Developers who need local access to Kubernetes services.
  • Teams seeking to reduce environment-specific connection configuration.
  • Users who need to forward multiple services or avoid local port conflicts.
  • 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
  • Local development without a Kubernetes cluster.
  • Environments without cluster access or the ability to grant root/sudo privileges.
  • Simple single-service forwarding where service-name resolution, auto-reconnect, and monitoring are unnecessary.
  • 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
  • A kubectl configuration with access to the target Kubernetes cluster is required.
  • Root/sudo access is required to modify /etc/hosts and network interfaces.
  • Access through the Kubernetes API is required to establish service port forwards.
  • 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
  • The tool modifies the local /etc/hosts file and network interfaces, which can affect local service-name resolution.
  • Cluster services are forwarded to the local machine, so local applications may access services in the development cluster.
  • The tool requires privileged execution; its permissions should be appropriate for the target development environment.
  • 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, CursorClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools00