TradingAgentStack is an MCP server published by io.github.intoApex, hosted at tradingagentstack.com. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 11 tools, including search_tools, get_tool, list_category, compare_tools, broker_order_gating.
Verified results for AI trading bots, vaults and algo strategies, plus safety scores and incidents.
1,114 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
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.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Max results (default 10) |
| query * | 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 |
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
{
"name": "search_tools",
"title": "Search AI trading tools",
"description": "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.",
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 20,
"minimum": 1,
"description": "Max results (default 10)"
},
"query": {
"type": "string",
"description": "Words to match, e.g. 'options paper alpaca'"
},
"category": {
"type": "string",
"description": "Category slug, e.g. broker_mcp, data_api, ai_bot_platform"
},
"has_paper": {
"type": "boolean",
"description": "Only tools with a documented paper/demo/testnet mode"
},
"can_trade_live": {
"type": "boolean",
"description": "Only tools that can place real-money orders"
}
}
},
"annotations": {
"title": "Search AI trading tools",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Full facts for one tool: pricing, live vs paper, order approval, rate limits, safety score inputs and every source URL.
| Parameter | Type | Description |
|---|---|---|
| slug * | string | Tool slug (from search_tools) or name |
{
"name": "get_tool",
"title": "Get tool facts and sources",
"description": "Full facts for one tool: pricing, live vs paper, order approval, rate limits, safety score inputs and every source URL.",
"inputSchema": {
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "Tool slug (from search_tools) or name"
}
}
},
"annotations": {
"title": "Get tool facts and sources",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List every tool in a category. Call with an unknown category to get the list of categories.
| Parameter | Type | Description |
|---|---|---|
| category * | string | Category slug, e.g. broker_mcp |
{
"name": "list_category",
"title": "List tools in a category",
"description": "List every tool in a category. Call with an unknown category to get the list of categories.",
"inputSchema": {
"type": "object",
"required": [
"category"
],
"properties": {
"category": {
"type": "string",
"description": "Category slug, e.g. broker_mcp"
}
}
},
"annotations": {
"title": "List tools in a category",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Compare two tools side by side, field by field, with sources.
| Parameter | Type | Description |
|---|---|---|
| slug_a * | string | |
| slug_b * | string |
{
"name": "compare_tools",
"title": "Compare two tools",
"description": "Compare two tools side by side, field by field, with sources.",
"inputSchema": {
"type": "object",
"required": [
"slug_a",
"slug_b"
],
"properties": {
"slug_a": {
"type": "string"
},
"slug_b": {
"type": "string"
}
}
},
"annotations": {
"title": "Compare two tools",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Who places the order for every official broker MCP server: AI trades directly, you confirm each order, approval optional, or you place the order.
No parameters.
{
"name": "broker_order_gating",
"title": "Broker MCP order approval overview",
"description": "Who places the order for every official broker MCP server: AI trades directly, you confirm each order, approval optional, or you place the order.",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"title": "Broker MCP order approval overview",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Check a tool before your agent connects to it: how much money could be lost if the tool, or the agent using it, is wrong, hacked or prompt-injected? Returns the Safety score (human approval, guardrails outside the agent, test mode, sending funds out, who holds the keys, open source or audited, incident record), each input with its reason and source; missing inputs are listed, not guessed. Omit tool to rank every tool in a category (e.g. agent_wallet, bot_exchange, broker_mcp).
| Parameter | Type | Description |
|---|---|---|
| tool | string | Tool slug or name, e.g. 'safe-smart-account', 'Hyperliquid' |
| category | string | Rank a category instead, e.g. agent_wallet, agent_payments, ai_trading_agent, bot_exchange, defi_agent or broker_mcp |
{
"name": "get_risk",
"title": "Safety score for a tool",
"description": "Check a tool before your agent connects to it: how much money could be lost if the tool, or the agent using it, is wrong, hacked or prompt-injected? Returns the Safety score (human approval, guardrails outside the agent, test mode, sending funds out, who holds the keys, open source or audited, incident record), each input with its reason and source; missing inputs are listed, not guessed. Omit tool to rank every tool in a category (e.g. agent_wallet, bot_exchange, broker_mcp).",
"inputSchema": {
"type": "object",
"properties": {
"tool": {
"type": "string",
"description": "Tool slug or name, e.g. 'safe-smart-account', 'Hyperliquid'"
},
"category": {
"type": "string",
"description": "Rank a category instead, e.g. agent_wallet, agent_payments, ai_trading_agent, bot_exchange, defi_agent or broker_mcp"
}
}
},
"annotations": {
"title": "Safety score for a tool",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}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 or a bot, exchange or wallet tracked by check.
| Parameter | Type | Description |
|---|---|---|
| tool | string | Only incidents for this tool or service (slug or name), e.g. 'alpaca-mcp-server', 'Keystone', 'Bloom' |
| since | string | Only incidents on or after this date, YYYY-MM-DD |
{
"name": "get_incidents",
"title": "Agent security incidents",
"description": "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 or a bot, exchange or wallet tracked by check.",
"inputSchema": {
"type": "object",
"properties": {
"tool": {
"type": "string",
"description": "Only incidents for this tool or service (slug or name), e.g. 'alpaca-mcp-server', 'Keystone', 'Bloom'"
},
"since": {
"type": "string",
"description": "Only incidents on or after this date, YYYY-MM-DD"
}
}
},
"annotations": {
"title": "Agent security incidents",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}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, what the service collects about you and any data breaches, incidents, deadlines and a 3-step safe setup, each with sources. For a hardware wallet (by name, maker or website: Ledger, Trezor, Coldcard, OneKey, BitBox, Tangem, Keystone, Jade, Passport, CoolWallet) it also returns the custody score from tradingagentstack.com/custody/. For a shop, it says which maker names it on its own authorized-reseller list (Ledger, Trezor, BitBox, CoolWallet), flags marketplaces, and flags shops whose reseller authorization was revoked. Unknown links are reported as unknown, never as safe.
| Parameter | Type | Description |
|---|---|---|
| query * | string | e.g. 't.me/solana_trojanbot', 'bananagun.io', '@krakenfx', 'github.com/cake-tech/cake_wallet', 'Kraken' |
{
"name": "check",
"title": "Check a bot, exchange or wallet before connecting",
"description": "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, what the service collects about you and any data breaches, incidents, deadlines and a 3-step safe setup, each with sources. For a hardware wallet (by name, maker or website: Ledger, Trezor, Coldcard, OneKey, BitBox, Tangem, Keystone, Jade, Passport, CoolWallet) it also returns the custody score from tradingagentstack.com/custody/. For a shop, it says which maker names it on its own authorized-reseller list (Ledger, Trezor, BitBox, CoolWallet), flags marketplaces, and flags shops whose reseller authorization was revoked. Unknown links are reported as unknown, never as safe.",
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "e.g. 't.me/solana_trojanbot', 'bananagun.io', '@krakenfx', 'github.com/cake-tech/cake_wallet', 'Kraken'"
}
}
},
"annotations": {
"title": "Check a bot, exchange or wallet before connecting",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Check a whole setup at once: up to 8 bots, exchanges, wallets, swap services or AI trading connectors someone uses (names, links, @handles or slugs). For each: who holds the keys, the worst case, who places orders, the Safety score, incidents in the last 12 months and the first fix, each from the dataset. Also returns the single biggest risk by a fixed rule, items we don't track (reported as unknown, never as safe), and a report_url that opens the same report on tradingagentstack.com. Links that use a tracked name but aren't official are flagged.
| Parameter | Type | Description |
|---|---|---|
| items * | array | e.g. ['Phantom', 'Trojan', 'Binance', 'Alpaca MCP server'] |
{
"name": "check_setup",
"title": "Check my whole setup",
"description": "Check a whole setup at once: up to 8 bots, exchanges, wallets, swap services or AI trading connectors someone uses (names, links, @handles or slugs). For each: who holds the keys, the worst case, who places orders, the Safety score, incidents in the last 12 months and the first fix, each from the dataset. Also returns the single biggest risk by a fixed rule, items we don't track (reported as unknown, never as safe), and a report_url that opens the same report on tradingagentstack.com. Links that use a tracked name but aren't official are flagged.",
"inputSchema": {
"type": "object",
"required": [
"items"
],
"properties": {
"items": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 8,
"description": "e.g. ['Phantom', 'Trojan', 'Binance', 'Alpaca MCP server']"
}
}
},
"annotations": {
"title": "Check my whole setup",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Verified performance leaderboard for AI trading agents, bots and vaults: return, BTC over the same dates, max drawdown and Sortino ratio, computed by TradingAgentStack from the venue's public API (never screenshots, self-reported PnL or backtests), with security rated separately as a gate. Sections: ai_vaults (Hyperliquid vaults whose leader says they are AI-run, with the quoted claim), vaults (biggest Hyperliquid vaults of any strategy), agents (AI agents with an officially published trading account or on-chain registration), apps (AI trading apps on Hyperliquid: users, volume and users' realized PnL from public builder fills), models (which AI model forecasts and trades best: ForecastBench, Prophet Arena, Alpha Arena, FutureEval), signals (grade B: MQL5 robot signals on real accounts, venue-reported, not ranked), usage (fees users pay Telegram bots, trading apps and AI agent protocols, and open-source repo health). Ranked vaults passed a 30% drawdown gate and are sorted by Sortino; the rest are listed as high_drawdown. Not investment advice.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Max entries per list (default 10) |
| section | string | Which list to return (default all: the verified lists plus apps; models, signals and usage only when asked) |
{
"name": "get_leaderboard",
"title": "Verified AI trading leaderboard",
"description": "Verified performance leaderboard for AI trading agents, bots and vaults: return, BTC over the same dates, max drawdown and Sortino ratio, computed by TradingAgentStack from the venue's public API (never screenshots, self-reported PnL or backtests), with security rated separately as a gate. Sections: ai_vaults (Hyperliquid vaults whose leader says they are AI-run, with the quoted claim), vaults (biggest Hyperliquid vaults of any strategy), agents (AI agents with an officially published trading account or on-chain registration), apps (AI trading apps on Hyperliquid: users, volume and users' realized PnL from public builder fills), models (which AI model forecasts and trades best: ForecastBench, Prophet Arena, Alpha Arena, FutureEval), signals (grade B: MQL5 robot signals on real accounts, venue-reported, not ranked), usage (fees users pay Telegram bots, trading apps and AI agent protocols, and open-source repo health). Ranked vaults passed a 30% drawdown gate and are sorted by Sortino; the rest are listed as high_drawdown. Not investment advice.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"maximum": 50,
"minimum": 1,
"description": "Max entries per list (default 10)"
},
"section": {
"enum": [
"all",
"ai_vaults",
"vaults",
"agents",
"apps",
"models",
"signals",
"usage"
],
"type": "string",
"description": "Which list to return (default all: the verified lists plus apps; models, signals and usage only when asked)"
}
}
},
"annotations": {
"title": "Verified AI trading leaderboard",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Look up one verified track record by Hyperliquid vault address, vault URL or name, Lighter public pool index or URL, dHEDGE vault address, or the address of an AI agent whose operator published its Hyperliquid or Polymarket account: return, BTC over the same dates, max drawdown, Sortino, 30-day return and TVL (for Polymarket agents: ROI on money put in, PnL and win rate), computed by TradingAgentStack from Hyperliquid's public API (not self-reported), with the window, the data date, whether it passes the 30% drawdown gate and until when it is fresh, and a SHA-256 of the record so an agent can cite exactly what it read. On the hosted endpoint the hash also comes signed (an ES256 JWT whose public keys are published), so anyone can check later that TradingAgentStack issued that exact record. Unknown addresses come back as not_tracked with how to get verified. Not investment advice.
| Parameter | Type | Description |
|---|---|---|
| query * | string | Vault or agent account address (0x...), app.hyperliquid.xyz/vaults/ URL, or vault or agent name |
{
"name": "get_track_record",
"title": "Look up one verified track record",
"description": "Look up one verified track record by Hyperliquid vault address, vault URL or name, Lighter public pool index or URL, dHEDGE vault address, or the address of an AI agent whose operator published its Hyperliquid or Polymarket account: return, BTC over the same dates, max drawdown, Sortino, 30-day return and TVL (for Polymarket agents: ROI on money put in, PnL and win rate), computed by TradingAgentStack from Hyperliquid's public API (not self-reported), with the window, the data date, whether it passes the 30% drawdown gate and until when it is fresh, and a SHA-256 of the record so an agent can cite exactly what it read. On the hosted endpoint the hash also comes signed (an ES256 JWT whose public keys are published), so anyone can check later that TradingAgentStack issued that exact record. Unknown addresses come back as not_tracked with how to get verified. Not investment advice.",
"inputSchema": {
"type": "object",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"description": "Vault or agent account address (0x...), app.hyperliquid.xyz/vaults/ URL, or vault or agent name"
}
}
},
"annotations": {
"title": "Look up one verified track record",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Read-only directory of AI trading tools, broker connectors, risk ratings and incident records. search_tools returns matching directory entries for a text query. get_tool returns the facts, sources and scores for one tool. list_category returns the tools in one category, or the category list if that slug is not a category. compare_tools returns a field-by-field comparison of two tools. broker_order_gating returns who places the order for each official broker MCP server. get_risk returns the Safety score for one tool, with each input, its reason and source, or a ranking for one category. get_incidents returns security incidents taken from official disclosures, for a listed tool or a tracked bot, exchange or wallet. get_leaderboard returns verified performance (return, BTC benchmark, max drawdown, Sortino) computed from public venue data for AI-labelled and large Hyperliquid vaults and registered AI agents, with the security gate; also AI trading apps on Hyperliquid, AI model benchmarks, venue-reported robot signals and bot usage stats. get_track_record returns one verified track record for a Hyperliquid vault, or for an AI agent whose operator published its Hyperliquid or Polymarket account, with the window, data date and a SHA-256 of the record; the hosted endpoint adds a signed attestation. check returns whether a name, link or handle is official, listed, a known fake, a lookalike or unknown, plus the stored custody, privacy and incident facts for a tracked service, the custody score for a hardware wallet, and any revoked reseller it names. check_setup returns one report for a list of bots, exchanges, wallets and connectors: keys, worst case, order approval, score, recent incidents and first fix for each, the biggest risk, and a shareable report link. Not financial advice. Verify with the vendor.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.