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.

DimensionQuant2Ptrader MCP ServerOne-click MCP server that converts JoinQuant strategies to the Ptrade platformMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS51 / 100 · D79 / 100 · B
Reliability8 / 2012 / 20
Security and permissions9 / 2018 / 20
Maintenance8 / 2016 / 20
Documentation14 / 2018 / 20
Setup experience12 / 2015 / 20
Best for
  • Quant traders using both JoinQuant and Ptrade who need to migrate strategies
  • Developers who want fast automated API-difference replacements plus clear notes on what still needs manual work
  • 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 guaranteed support for JoinQuant research-environment APIs or third-party libraries
  • Anyone expecting production/live trading use without manual review
  • Strategy conversion for platforms other than JoinQuant/Ptrade
  • 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
  • Reads local strategy files (.py, .txt, .text, .code, .strategy)
  • Writes generated _ptrade.py files to the working directory, the source file's directory, or a specified output_dir
  • 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
  • order_target_percent is converted to order_target_value; target amounts must be calculated manually
  • run_weekly/run_monthly become run_daily and require custom date-check logic inside the function
  • get_fundamentals query syntax may need tweaks; datetime parameters should use string format
  • Some JoinQuant-specific research-environment APIs may not convert fully; custom functions and third-party libraries need manual compatibility checks
  • Converted strategies should be validated with small-scale backtests on Ptrade before any live use
  • 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
Tools10