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.

DimensionFlyEnvManage local dev stacks, AI coding CLIs, and MCP nativelyMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS41 / 100 · D79 / 100 · B
Reliability4 / 2012 / 20
Security and permissions5 / 2018 / 20
Maintenance13 / 2016 / 20
Documentation10 / 2018 / 20
Setup experience9 / 2015 / 20
Best for
  • Full-stack developers wanting XAMPP/MAMP/Herd-style convenience
  • Developers working with multiple runtime versions across projects
  • Developers building local AI coding workflows
  • Developers needing databases, queues, search, and other local services
  • 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
  • Those needing exact Docker Compose or Kubernetes parity with production
  • Developers who only use one runtime and are happy with system package manager
  • Those preferring to manage every service manually from terminal
  • Those needing hosted platform or production deployment system
  • 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
  • System-level installation: requires permissions to install packages to system directories
  • Network access: may start local services and listen on ports, access internet to download dependencies
  • File system access: read/write project files, configs, and logs
  • Process management: start, stop, and monitor local processes
  • 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
  • Third-party software: downloaded runtimes and services come from third parties, posing supply chain risks
  • Misconfiguration: improper configuration may cause port conflicts or security vulnerabilities
  • System modification: may modify system PATH or install global tools
  • Data security: local databases may contain sensitive data, ensure proper protection
  • 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 DesktopClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools50