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.

DimensionAI as WorkspaceCross-platform AI chat client with MCP support and local-first storage.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS47 / 100 · D79 / 100 · B
Reliability8 / 2012 / 20
Security and permissions11 / 2018 / 20
Maintenance6 / 2016 / 20
Documentation12 / 2018 / 20
Setup experience10 / 2015 / 20
Best for
  • Users who want a consistent AI chat experience across multiple operating systems
  • Users who prefer local-first conversation storage with optional cloud sync
  • Users who want to consume tools, prompts and resources through the MCP protocol
  • Advanced users who value plugins and dynamic prompt variables for customization
  • 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 looking for an actively maintained project (this one is deprecated; migration to Nya AI is recommended)
  • Users who only need a simple command-line tool without a graphical interface
  • Enterprise-grade centralized control or strict compliance auditing scenarios
  • 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
  • Network access: connect to configured AI providers (OpenAI, Anthropic, Google, DeepSeek, xAI, Azure, etc.)
  • Local storage/file system: store data and file attachments locally first
  • Process execution: launch local MCP server processes over STDIO
  • Cloud account: used for cross-device data synchronization after login
  • 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 project is deprecated and may no longer receive security updates or feature fixes
  • Local MCP servers launched over STDIO inherit client process permissions; only add servers you trust
  • Cloud sync uploads data to a server, creating privacy and data leakage risks
  • Plugins and third-party services may access conversation content, risking data exposure when untrusted
  • Connecting to third-party AI providers sends conversation content to those providers
  • 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
Tools00