TradingAgentStack

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Read-only, sourced directory of 114 AI trading tools, broker MCP servers and market data APIs.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "TradingAgentStack": {
      "url": "https://tradingagentstack.com/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (8)

• search_tools read-only

  Search the TradingAgentStack directory of AI trading tools (broker MCP servers, trading and data APIs, bots, frameworks) by name, market or feature. Optional filters: category slug, can_trade_live, has_paper.

  Parameters:

  • query (required) — string — Words to match, e.g. 'options paper alpaca'
  • category — string — Category slug, e.g. broker_mcp, data_api, ai_bot_platform
  • has_paper — boolean — Only tools with a documented paper/demo/testnet mode
  • can_trade_live — boolean — Only tools that can place real-money orders

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_tool read-only

  Full facts for one tool: pricing, live vs paper, order approval, rate limits, safety score inputs and every source URL.

  Parameters:

  • slug (required) — string — Tool slug (from search_tools) or name

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_category read-only

  List every tool in a category. Call with an unknown category to get the list of categories.

  Parameters:

  • category (required) — string — Category slug, e.g. broker_mcp

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• compare_tools read-only

  Compare two tools side by side, field by field, with sources.

  Parameters:

  • slug_a (required) — string
  • slug_b (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• broker_order_gating read-only

  Who places the order for every official broker MCP server: AI trades directly, you confirm each order, approval optional, or you place the order.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_risk read-only

  Check a tool before your agent connects to it: how much money could the agent lose if it is wrong, hacked or prompt-injected? Returns the Agent Risk Score (custody, limits enforced outside the model, human approval, withdrawal scope, preview, open source, incident record), each input with its official source; missing inputs are listed, not guessed. Omit tool to rank every scored tool in a category (agent_wallet, agent_payments, ai_trading_agent, agent_token, bot_exchange, defi_agent).

  Parameters:

  • tool — string — Tool slug or name, e.g. 'safe-smart-account', 'Hyperliquid'
  • category — string — Rank a category instead: agent_wallet, agent_payments, ai_trading_agent, agent_token, bot_exchange or defi_agent

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_incidents read-only

  Security incidents involving AI agents, trading tools and the infrastructure they run on (breaches, exploits, security releases), each from an official disclosure. Filter by date or by a listed tool.

  Parameters:

  • tool — string — Only incidents naming this tool (slug or name)
  • since — string — Only incidents on or after this date, YYYY-MM-DD

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• check read-only

  Check before connecting (TAS Check): give a name, link, Telegram or X @handle, GitHub repo or app-store link of a Telegram trading bot, web trading terminal, exchange, swap service or wallet (incl. Zcash/Monero wallets). Returns whether the link is on that service's official list (confirmed from two independent places), a known fake, or a lookalike that uses its name, plus the worst case for your money, who holds the keys, freeze/hold policy, what a leaked API key can do, Monero/Zcash support, incidents, deadlines and a 3-step safe setup, each with sources. Unknown links are reported as unknown, never as safe.

  Parameters:

  • query (required) — string — e.g. 't.me/solana_trojanbot', 'bananagun.io', '@krakenfx', 'github.com/cake-tech/cake_wallet', 'Kraken'

  Hints: read-only yes · destructive no · idempotent yes · open-world no

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.