TradingAgentStack

npx add-mcp 'https://tradingagentstack.com/api/mcp'

TradingAgentStack MCP Server

Know what an AI trading tool can do with your money before you connect it.

A free, read-only Model Context Protocol server for the TradingAgentStack directory of over 140 AI trading tools, including broker MCP servers, market data APIs and MCPs, agent frameworks, backtesters, trading bots, prediction market APIs, and VPS hosts. It also returns Agent Risk Scores, incident records, and a TAS Check verdict for a bot, exchange, swap service, or wallet link.

Every answer includes the vendor's source URLs and the date the fact was last checked.

• Endpoint (streamable HTTP): https://tradingagentstack.com/api/mcp
• Auth: none. Free, no sign-in, read-only, no write access to anything.
• Docs: https://tradingagentstack.com/mcp/

Tools

Checked against tools/list on the hosted endpoint (server version 0.5.0) on 2026-10-27. The same eight tools, with the same descriptions and inputs, are in the published npm package tradingagentstack-mcp@0.5.0.

Tool	What it does
search_tools(query, category?, can_trade_live?, has_paper?)	Search by name, market, or feature
get_tool(slug)	Every fact for one tool, with sources and safety inputs
list_category(category)	All tools in a category. An unknown category returns the category list
compare_tools(slug_a, slug_b)	Side-by-side comparison
broker_order_gating()	Who places the order for every broker MCP server (you, or the AI)
get_risk(tool?, category?)	Agent Risk Score for one tool, or a ranking for a category. Each input has a source. Missing inputs are listed, not guessed
get_incidents(since?, tool?)	Security incidents from official disclosures, filtered by date (YYYY-MM-DD) or tool
check(query)	TAS Check: whether a name, link, @handle, or GitHub repo is official, a known fake, or a lookalike, plus custody, freeze, API-key risk, incidents, and a short safe setup. Unknown is not safe

npm package and this repository

The recommended way to run the server is the published npm package:

npx -y tradingagentstack-mcp

That command installs the current npm release. The release is 0.5.0, and its binary is tradingagentstack-mcp (src/index.js). The package is built from intoApex/ai-trading-tools (mcp-server). Its tool list matches the hosted endpoint at https://tradingagentstack.com/api/mcp. Use that URL when you want the same server with no local process.

This repository's own code is older. It is still version 0.3.2. npm run build and node dist/index.js in this checkout start that older stdio server. It implements only search_tools, get_tool, list_category, compare_tools, and broker_order_gating. It has no bundled dataset.

Three differences remain between the published package and the hosted server:

• The hosted server tells the client to call get_risk before connecting an agent to a wallet, exchange, or trading tool. The npm stdio server introduces itself as a read-only directory of AI trading tools.
• Hosted tools/list gives each tool a title and marks it read-only, non-destructive, idempotent, and closed-world (openWorldHint: false). The npm stdio server sets readOnlyHint: true and openWorldHint: true.
• If the live dataset fetch fails, the npm package serves a copy bundled in 0.5.0 (133 tools, generated 2026-10-23). On 2026-10-27 the live file https://tradingagentstack.com/data/tools.json reported meta.count 143 (generated 2026-10-26). The site homepage lists the same live total.

Install

Run the published npm package, or connect to the hosted endpoint. Both are the current eight-tool server. Building this repository is the older five-tool server, under Build from source.

Node.js 18 or later is required for the npm package. The hosted endpoint needs no install and no API key.

An agent can follow llms-install.md on its own.

Cline

No API key. Add one server named tradingagentstack. The settings file is ~/.cline/data/settings/cline_mcp_settings.json (Windows: %USERPROFILE%\.cline\data\settings\cline_mcp_settings.json), unless CLINE_MCP_SETTINGS_PATH is set. In the Cline panel, open it from the MCP Servers icon, then Configure, then Configure MCP Servers. Step-by-step instructions for an agent are in llms-install.md.

Published npm package (recommended local run):

{
  "mcpServers": {
    "tradingagentstack": {
      "command": "npx",
      "args": ["-y", "tradingagentstack-mcp"],
      "disabled": false,
      "autoApprove": []
    }
  }
}

cline mcp add tradingagentstack --yes -- npx -y tradingagentstack-mcp

Hosted endpoint. "type": "streamableHttp" is required. A URL with no type is legacy SSE, and this endpoint is streamable HTTP.

{
  "mcpServers": {
    "tradingagentstack": {
      "type": "streamableHttp",
      "url": "https://tradingagentstack.com/api/mcp",
      "disabled": false,
      "autoApprove": []
    }
  }
}

cline mcp add tradingagentstack https://tradingagentstack.com/api/mcp --transport http --yes

Gemini CLI

gemini-extension.json starts the published package with npx -y tradingagentstack-mcp. GEMINI.md is the context file Gemini CLI loads with the extension.

gemini extensions install https://github.com/intoApex/tradingagentstack-mcp

Restart Gemini CLI after installing.

The extension gallery lists a public GitHub repository after it has the topic gemini-cli-extension and a gemini-extension.json file at the repository root. The crawler runs daily. Add the topic in the repository About settings.

Claude Code

Hosted endpoint:

claude mcp add --transport http tradingagentstack https://tradingagentstack.com/api/mcp

Project config (.mcp.json in this repo). Claude Code asks you to approve it the first time:

{
  "mcpServers": {
    "tradingagentstack": {
      "type": "http",
      "url": "https://tradingagentstack.com/api/mcp"
    }
  }
}

Published npm package:

claude mcp add tradingagentstack -- npx -y tradingagentstack-mcp

Claude Desktop / claude.ai: Settings → Connectors → Add custom connector → paste https://tradingagentstack.com/api/mcp

Claude Desktop (local, via npm): add this to claude_desktop_config.json (Settings → Developer → Edit Config), then restart Claude Desktop.

{
  "mcpServers": {
    "tradingagentstack": {
      "command": "npx",
      "args": ["-y", "tradingagentstack-mcp"]
    }
  }
}

Cursor

Hosted endpoint, in .cursor/mcp.json:

{
  "mcpServers": {
    "tradingagentstack": { "url": "https://tradingagentstack.com/api/mcp" }
  }
}

Published npm package, in .cursor/mcp.json:

{
  "mcpServers": {
    "tradingagentstack": {
      "command": "npx",
      "args": ["-y", "tradingagentstack-mcp"]
    }
  }
}

Hosted endpoint

Any client that supports remote MCP over streamable HTTP:

https://tradingagentstack.com/api/mcp

No API key and no sign-in.

Example prompts

• "Which broker MCP servers let the AI place live orders without my confirmation?"
• "Compare Alpaca MCP and IBKR MCP for paper trading."
• "Find free market data APIs that cover crypto and US stocks."
• "What safeguards does the Robinhood Trading MCP have?"
• "Before I connect this wallet, call get_risk and tell me what it could lose."
• "Is this Telegram bot link official, or a lookalike?"

Data

The hosted server and the npm package read the open dataset at https://tradingagentstack.com/data/ (JSON and CSV, CC BY 4.0). The current size is meta.count in tools.json. Also available for LLMs: llms.txt and llms-full.txt.

Missing a tool or spotted an outdated fact? Submit it or open an issue.

Build from source

This path is for working on the older code in this repository. The recommended run command is npx -y tradingagentstack-mcp, the published package built from intoApex/ai-trading-tools (mcp-server).

npm install
npm run build
node dist/index.js   # stdio server from this repo (0.3.2, five tools)

That local server fetches https://tradingagentstack.com/data/tools.json and caches it in memory for one hour. Set TAS_DATA_URL to point it at another copy of the dataset. It does not include get_risk, get_incidents, or check. For those, use the hosted endpoint or npx -y tradingagentstack-mcp.

Disclaimer

Not financial advice. Verify every fact with the vendor before connecting any tool to a funded account.