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.

DimensionNeuroLinkThe TypeScript pipe layer for the AI nervous system.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS46 / 100 · D79 / 100 · B
Reliability8 / 2012 / 20
Security and permissions8 / 2018 / 20
Maintenance10 / 2016 / 20
Documentation11 / 2018 / 20
Setup experience9 / 2015 / 20
Best for
  • TypeScript teams needing a unified API across multiple AI providers
  • Applications requiring MCP integration, RAG, memory, or provider failover
  • Developers who want both an SDK and a professional CLI
  • 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 seeking a standalone MCP server with a verified tool manifest and transport
  • Users unwilling to configure AI provider credentials
  • Simple MCP use cases that do not need a TypeScript SDK, CLI, or multi-provider features
  • 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
  • API credentials for configured AI providers
  • Appropriate local file read permissions when processing files
  • File write permissions when using the built-in writeFile tool
  • Tokens, environment variables, or authorization required by connected external MCP servers
  • ffmpeg or bundled ffmpeg-static may be required for video processing
  • 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
  • Prompts, files, or audio may be sent to the selected AI provider; data handling depends on provider configuration
  • writeFile and external MCP tools may modify data or trigger external actions
  • Invalid credentials, rate limits, or provider outages can cause requests to fail
  • Tokens and permission scopes for external MCP servers affect the security boundary
  • Audio, video, and large-context processing may require additional dependencies or resources
  • 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
Tools60