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.

DimensionUpsonicBuild autonomous AI agents in PythonMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS34 / 100 · D79 / 100 · B
Reliability4 / 2012 / 20
Security and permissions7 / 2018 / 20
Maintenance9 / 2016 / 20
Documentation9 / 2018 / 20
Setup experience5 / 2015 / 20
Best for
  • Developers building AI agents in Python
  • Autonomous-agent projects requiring workspace-scoped file and shell operations
  • Projects needing custom tools or OCR capabilities
  • 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 seeking a ready-made MCP server tool catalog
  • Users requiring verified transport, authentication, or client configuration details
  • Projects that need unrestricted file or shell operations without an isolated environment
  • 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
  • Autonomous-agent file and shell operations are restricted to the specified workspace
  • The README does not document additional MCP-server permissions, authentication, or external-service access requirements
  • 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
  • Autonomous agents perform file and shell operations; although the README says path traversal and dangerous commands are blocked, the workspace scope should still be reviewed
  • A sandbox provider is described as a next step; the README mentions E2B but does not specify security settings
  • The supplied material does not establish that the repository itself exposes a directly connectable MCP server
  • 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 Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools00