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.

DimensionRobinhood for AgentsRobinhood integration for AI agents — 50 MCP tools + TypeScript client library.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS43 / 100 · D79 / 100 · B
Reliability6 / 2012 / 20
Security and permissions7 / 2018 / 20
Maintenance7 / 2016 / 20
Documentation12 / 2018 / 20
Setup experience11 / 2015 / 20
Best for
  • Developers comfortable with Robinhood and programming.
  • Users needing to enable AI agents to execute trading actions.
  • Users wanting to integrate Robinhood data into AI workflows.
  • 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 unfamiliar with Robinhood or without a Robinhood account.
  • Users seeking an officially supported Robinhood API.
  • Users who cannot accept the risks of AI-driven trading.
  • Users preferring a login method other than browser-based.
  • 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 and modify Robinhood account data (positions, orders, watchlists, etc.).
  • Perform login via Chrome browser and capture OAuth tokens (passive).
  • Access OS keychain or encrypted file for token storage.
  • Make network requests to Robinhood's public interfaces.
  • 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 may misinterpret intent and place unintended orders, causing financial loss.
  • Market data may be stale or inaccurate.
  • Software bugs or unexpected behavior could lead to erroneous trades.
  • Token storage risk: encrypted files can be decrypted by malicious agents with shell access in containers.
  • Session refresh failures may leave the container unable to re-authenticate after restart.
  • This is an unofficial tool; use at your own risk.
  • 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, Codex, OpenClawClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools500