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.

DimensionNakkas MCP ServerMCP server that turns AI into an SVG artist. One rendering engine, AI decides everything.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS66 / 100 · C79 / 100 · B
Reliability11 / 2012 / 20
Security and permissions13 / 2018 / 20
Maintenance11 / 2016 / 20
Documentation17 / 2018 / 20
Setup experience14 / 2015 / 20
Best for
  • Users of MCP-enabled AI assistants like Claude, Cursor, or Zed
  • Projects needing animated SVGs without JavaScript
  • Those embedding animations on GitHub or web pages
  • Designers aiming to quickly prototype and iterate generated vector graphics
  • 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
  • SVG applications requiring JavaScript interactivity (e.g., onclick)
  • Scenarios depending on external fonts (GitHub won't load them)
  • Long-term persistence of artifacts (they live only for the server process, capped at 32)
  • Complex nested group structures (nested groups are not supported)
  • 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
  • Local file system write access (for the save tool)
  • Access to network to load images if URLs are specified
  • Running a local server process (stdio transport)
  • 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 save tool can overwrite files (though it appends a counter to avoid overwriting)
  • Designs may not render correctly on GitHub if they use scripts or external fonts
  • Large or complex animations may result in large output sizes
  • MCP client serialization quirks may cause validation errors
  • 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, Claude Code, Cursor, ZedClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools30