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.

Dimension1Password MCP ServerGive your AI assistant a locked door to 1Password — not a pile of passwords in the chatMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS75 / 100 · B79 / 100 · B
Reliability12 / 2012 / 20
Security and permissions16 / 2018 / 20
Maintenance14 / 2016 / 20
Documentation18 / 2018 / 20
Setup experience15 / 2015 / 20
Best for
  • Individuals and teams managing automation credentials like CI tokens and bot accounts
  • Security-conscious users who want to keep plaintext out of model transcripts
  • Developers and SREs using MCP clients such as Claude Desktop, Cursor, VS Code Copilot, or OpenAI Codex
  • 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
  • Storing banking, primary personal logins, or recovery codes
  • Workflows where nothing may be sent to an AI provider
  • Scenarios requiring end-to-end encryption of secrets in transit
  • Users without a Node.js 20+ runtime
  • 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 1Password service account token (or a macOS Keychain token)
  • The service account must be granted access to target vaults
  • op_run can execute arbitrary local commands (with cwd, shell, timeout, stdin options)
  • item_delete permanently removes items with no undo
  • 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
  • Anything revealed to the model may be sent to your AI provider and retained under their policies
  • Secrets are plaintext inside the MCP workflow — not end-to-end encrypted; encrypted only at rest in 1Password
  • The service account token is a master key and must be rotated immediately if leaked
  • item_delete is irreversible
  • op_run allows local command execution — pair with vault allow-lists and least-privilege scoping
  • 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, Cursor, VS Code, Codex, GeminiClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools150