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.

DimensionClaude Task MasterAn AI-powered task management system that drops into Cursor, Lovable, Windsurf, Roo, and more.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS47 / 100 · D79 / 100 · B
Reliability7 / 2012 / 20
Security and permissions8 / 2018 / 20
Maintenance15 / 2016 / 20
Documentation9 / 2018 / 20
Setup experience8 / 2015 / 20
Best for
  • Product managers and developers who want to manage development tasks directly from AI chat
  • Users of AI editors like Cursor, Windsurf, VS Code
  • Teams needing to automate task generation from requirements documents (PRDs)
  • Developers looking to minimize context window usage and optimize AI tool loading
  • 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
  • Traditional project management scenarios without AI assistance
  • Environments without any API key and without Claude Code or Codex CLI installed
  • Users seeking fully offline, dependency-free task management
  • Those who need commercial hosting or want to resell the software (license limitations)
  • 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 project files (e.g., PRD documents)
  • Create and modify task files in the project directory (e.g., .taskmaster folder)
  • Execute the task-master-ai package via npx
  • Access external AI APIs (e.g., Anthropic, OpenAI) to generate and analyze tasks
  • 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
  • AI-generated tasks may be inaccurate and require human review
  • Project file data is sent to external AI services, posing potential data leakage risks
  • API keys in config files could be leaked and misused
  • Non-official server with MIT with Commons Clause license; resale or hosting is prohibited
  • Large default toolset (36) may increase context consumption; configuration optimization recommended
  • 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, Windsurf, VS Code, Q CLIClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools150