About TradingAgentStack
TradingAgentStack is a read-only MCP server for clients that need to research broker, market-data, and trading-agent tools. Its directory records safety controls, pricing, rate limits, sources, and check dates; it cannot connect to brokers or place trades.
Key features
- 01Search tools by keyword and category
- 02Retrieve a tool’s full record
- 03Compare two broker tools
- 04List categories and counts
- 05Review safety, pricing, limits, and sources
Use cases
- 01Find broker servers that support paper trading
- 02Compare broker safety controls before choosing
- 03Review an entry’s source and last-checked date
MCP support
Exposes directory search, record lookup, broker comparison, and category listing tools to MCP clients. It only reads its dataset and does not connect to brokers or execute trades.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://tradingagentstack.com/api/mcpclaude mcp add --transport http intoapex-tradingagentstack https://tradingagentstack.com/api/mcp{"mcpServers":{"intoapex-tradingagentstack":{"type":"http","url":"https://tradingagentstack.com/api/mcp"}}}Open in Cursor{"servers":{"intoapex-tradingagentstack":{"type":"http","url":"https://tradingagentstack.com/api/mcp"}}}Open in VS Code{"mcpServers":{"intoapex-tradingagentstack":{"type":"http","url":"https://tradingagentstack.com/api/mcp"}}}{"mcpServers":{"intoapex-tradingagentstack":{"serverUrl":"https://tradingagentstack.com/api/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
4| Parameter | Type | Required | Description |
|---|---|---|---|
| limit | integer | No | |
| query | string | No | Keywords, e.g. 'options paper trading' or 'crypto' |
| category | enum | No | Optional category filter (see list_categories)broker_mcp | data_mcp | broker_api | data_api | agent_framework | backtest_platform | trading_agent | security_tool |
Details
From the project READMETradingAgentStack MCP server
A small, read-only MCP server that lets Claude, Cursor and other MCP clients search the TradingAgentStack directory: broker MCP servers, broker and market-data APIs, agent frameworks, backtesters and security tools. Each entry includes paper vs live trading, order approval and safety controls, pricing, rate limits, an official source and a last-checked date.
It can't place trades or connect to any broker. It only reads the open dataset in ../data/tools.json (CC BY 4.0).
Tools
| Tool | What it does |
|---|---|
search_tools(query, category?, limit?) | Keyword search, with an optional category filter |
get_tool(slug) | Full record for one tool, e.g. alpaca-mcp-server |
compare_brokers(a, b) | Side-by-side comparison of two tools |
list_categories() | Categories with counts |
Example prompts: "Which broker MCP servers support paper trading?", "Compare Alpaca MCP and Tradier MCP on safety controls."
Install
Needs Node.js 18 or later.
Claude Desktop
Add this to claude_desktop_config.json (Settings → Developer → Edit Config):
{
"mcpServers": {
"tradingagentstack": { "command": "npx", "args": ["-y", "tradingagentstack-mcp"] }
}
}
Cursor
Add this to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):
{
"mcpServers": {
"tradingagentstack": { "command": "npx", "args": ["-y", "tradingagentstack-mcp"] }
}
}
Claude Code
claude mcp add tradingagentstack -- npx -y tradingagentstack-mcp
From source
git clone https://github.com/intoApex/ai-trading-tools && cd ai-trading-tools/mcp-server
npm install && npm test # copies ../data/tools.json and runs a stdio smoke test
node src/index.js # or point your client's "command" at this file
The server uses the dataset bundled with the package. To use the latest data from GitHub instead, set TRADINGAGENTSTACK_LIVE=1; it falls back to the bundled copy if the fetch fails.
License
The code is MIT. The data is CC BY 4.0 and should be credited to TradingAgentStack (tradingagentstack.com). Not financial advice.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.