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.

DimensionArgo CD MCP ServerAn MCP server for Argo CD, enabling AI assistants to interact with your Argo CD applications through natural language.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS71 / 100 · B79 / 100 · B
Reliability10 / 2012 / 20
Security and permissions16 / 2018 / 20
Maintenance16 / 2016 / 20
Documentation15 / 2018 / 20
Setup experience14 / 2015 / 20
Best for
  • DevOps teams wanting to use AI assistants with Argo CD.
  • Users with GitOps workflows needing natural language management of Kubernetes applications.
  • Developers using MCP within VS Code or Cursor.
  • 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
  • Production environments with strict security boundaries that cannot expose API tokens to AI assistants.
  • Multi-replica deployments without sticky sessions unless running `--stateless` mode.
  • 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 access to the Argo CD API, including read permissions for clusters, applications, resource trees, logs, events, etc.
  • Write operations (create, update, delete, sync, run action) require appropriate Argo CD RBAC permissions.
  • The server reads API tokens from environment variables or HTTP headers, never exposing them in tool calls.
  • 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
  • API tokens are sensitive; must be stored securely and not leaked.
  • Write operations can modify or delete applications; use with caution.
  • Disabling TLS verification for self-signed certificates reduces security.
  • Default token is bound to the default base URL to prevent credential exfiltration, but misconfiguration can cause fail-closed behavior.
  • 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, VS Code, CursorClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools140