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.

DimensionAI Experiment Logger MCP ServerMCP server for logging and analyzing AI experimentsMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS43 / 100 · D79 / 100 · B
Reliability7 / 2012 / 20
Security and permissions11 / 2018 / 20
Maintenance13 / 2016 / 20
Documentation5 / 2018 / 20
Setup experience7 / 2015 / 20
Best for
  • Developers who want lightweight tracking of AI experiments inside a Claude Code workflow
  • Users who prefer MCP tools over manual spreadsheets for managing experiment metadata
  • 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
  • Teams needing an enterprise-grade experiment tracking platform with versioning, collaboration, or cloud sync
  • Production deployments requiring official Anthropic support or independent security audits
  • 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 filesystem read/write access to persist experiment log data
  • Ability to run a Node.js process communicating with the MCP client over stdio
  • 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
  • This server comes from a community marketplace repository with hundreds of plugins; it is not maintained by Anthropic and has no stated independent security audit
  • Experiment records may contain sensitive data such as prompts or outputs, so local storage access should be controlled
  • Installing via a third-party CLI (ccpi) or marketplace script carries some supply-chain risk; review the source before installing
  • 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 CodeClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools70