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.

DimensionMiniClaudeLightweight local AI coding assistant, streamlined from Claude CodeMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS35 / 100 · D79 / 100 · B
Reliability5 / 2012 / 20
Security and permissions4 / 2018 / 20
Maintenance10 / 2016 / 20
Documentation8 / 2018 / 20
Setup experience8 / 2015 / 20
Best for
  • Developers concerned about privacy and local development
  • Individuals or teams needing a lightweight alternative to Claude Code
  • Developers familiar with Bun and TypeScript
  • 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 needing team collaboration and cloud sync features
  • Enterprises requiring official support and maintenance
  • Windows users not comfortable with command line
  • 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
  • Read and write project files
  • Execute shell commands (Bash/PowerShell)
  • Access Git repositories
  • Use network services (calling AI APIs)
  • 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
  • When using third-party APIs, be aware of data privacy; code may be sent to external model services
  • Project is not official, there may be security vulnerabilities or incomplete features
  • Depends on Bun runtime, ensure environment stability
  • 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
Tools00