Skip to main content
Glama
TradeStaq MCP

TradeStaq MCP

Official
by the-staq
README.md
# TradeStaq MCP Server

[![npm version](https://img.shields.io/npm/v/@the-staq/tradestaq-mcp)](https://www.npmjs.com/package/@the-staq/tradestaq-mcp)
[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)

**[Website](https://tradestaq.com)** · **[Docs](https://tradestaq.com/docs)** · **[MCP / AI Tools](https://tradestaq.com/mcp)** · **[Pricing](https://tradestaq.com/pricing)**

**46 AI-powered trading tools for Claude, Cursor, and any MCP client.**

Create strategies, backtest them, deploy trading bots, copy top traders, monitor positions, and manage your crypto portfolio, all from conversation. Supports Binance, Bybit, OKX, Bitget, Hyperliquid, dYdX, and more.

```
"Show me my portfolio" → get_portfolio
"Backtest GhostRider on BTC/USDT for 3 months" → what_if_backtest
"Deploy it on my Binance account" → deploy_bot
"Who are the top traders this month?" → list_top_traders
"Generate a momentum strategy for ETH" → generate_strategy
```

## Quick Start

### Option A: Remote server (no install needed)

For MCP clients that support HTTP transport:

```json
{
  "mcpServers": {
    "tradestaq": {
      "url": "https://mcp.tradestaq.com/mcp"
    }
  }
}
```

### Option B: npx (recommended for local)

No clone, no build. Just add to your MCP config:

**Claude Desktop** (`~/Library/Application Support/Claude/claude_desktop_config.json`):

```json
{
  "mcpServers": {
    "tradestaq": {
      "command": "npx",
      "args": ["-y", "@the-staq/tradestaq-mcp"]
    }
  }
}
```

**Cursor** (`.cursor/mcp.json`):

```json
{
  "mcpServers": {
    "tradestaq": {
      "command": "npx",
      "args": ["-y", "@the-staq/tradestaq-mcp"]
    }
  }
}
```

**Claude Code:**

```sh
claude mcp add tradestaq -- npx -y @the-staq/tradestaq-mcp
```

### Option C: Clone and build

```sh
git clone https://github.com/the-staq/tradestaq-mcp.git
cd tradestaq-mcp
npm install
npm run build
```

Then point your MCP client to `dist/index.js`.

## Authenticate

After adding the server, ask your AI assistant to log in:

- **"Log me in to TradeStaq"** — uses email/password directly
- **"Authenticate with TradeStaq"** — opens a browser window for secure OAuth login

Credentials never enter the chat when using the browser flow. Token is stored locally at `~/.tradestaq/mcp-config.json` with restricted permissions (0600).

## Tools

### Auth

| Tool | Description |
|------|-------------|
| `login` | Log in with email and password |
| `authenticate` | Log in via browser (OAuth + PKCE) |
| `check_auth` | Check authentication status |
| `set_token` | Manually set a JWT token |
| `connect_exchange` | Connect an exchange account via browser |
| `logout` | Remove stored credentials |

### Market Data

| Tool | Description |
|------|-------------|
| `get_price` | Current price, 24h change, volume |
| `get_candles` | OHLCV candlestick data (1m to 1d) |
| `list_exchanges` | List connected exchange accounts |
| `search_markets` | Find trading pairs on a specific exchange |

### Portfolio

| Tool | Description |
|------|-------------|
| `get_portfolio` | Total balance, exchanges, active bots |
| `get_positions` | Open positions with live PnL |

### Strategies

| Tool | Description |
|------|-------------|
| `list_strategies` | Browse marketplace or your own strategies |
| `get_strategy` | Full strategy details and performance |
| `explain_strategy` | Plain-English explanation with risk profile |
| `compare_strategies` | Side-by-side metrics comparison |
| `create_strategy` | Create a strategy from TradeDroid code |
| `generate_strategy` | Generate a strategy from natural language using AI |

### Backtesting

| Tool | Description |
|------|-------------|
| `what_if_backtest` | Run a historical backtest (async, 30-120s) |
| `get_backtest_results` | Check status of a running backtest |

### Bot Management

| Tool | Description |
|------|-------------|
| `list_bots` | All bots with status and performance |
| `get_bot_status` | Detailed bot metrics and config |
| `get_bot_logs` | Run-by-run history: why a bot did or did not trade, dropped signals, errors |
| `deploy_bot` | Deploy a strategy as a trading bot |
| `update_bot` | Edit a bot: rename, switch strategy or apply a preset, timeframe, execution mode, strategy parameters, version channel, risk settings, notifications, `stopAfterClose` |
| `start_bot` | Start a paused or stopped bot |
| `stop_bot` | Stop a running bot now (open positions are left unmanaged) |
| `delete_bot` | Delete a bot (refused while it has an open trade) |
| `close_position` | Close an open position (full or partial) |

`deploy_bot` defaults to paper trading. Pass `live: true` for real money. The bot trades on the strategy's own timeframe; pass `timeframe` (e.g. `4h`) only to override it. Leave out `name` and the server names the bot.

`update_bot` sends everything you pass in one update, after merging it onto the bot's current settings (position sizing, spin settings and parameter overrides are never wiped by a partial change). Size and leverage change only when you pass them. `strategyId` and `presetId` take an ID or a slug (`trade-wind`, `trade-wind-long-short`). A strategy or timeframe change needs the bot to be flat: pause it with `stopAfterClose: true` first, wait until `get_bot_status` shows no open position, then switch, then `start_bot`. A live bot needs the `mcp:live` scope for any change; a paper bot `mcp:paper`. The reply is the resulting config (strategy, version, timeframe, mode, overrides, size, leverage, status) plus server warnings.

For example, switching a paused 15m GhostRider bot to Trade Wind on 4h with its Long & Short preset, and renaming it:

```json
{ "id": "6ab7c2d60014ba19b0c54258", "presetId": "trade-wind-long-short", "timeframe": "4h", "name": "Trade Wind · SUI · 4h" }
```

### Trade History

| Tool | Description |
|------|-------------|
| `get_trade_history` | Closed trades with PnL, entry/exit prices |
| `get_performance_metrics` | ROI, win rate, Sortino ratio, PnL breakdown |

### Copy Trading

| Tool | Description |
|------|-------------|
| `list_top_traders` | Browse the leaderboard of top traders |
| `follow_trader` | Subscribe to copy a trader's trades |

### Advisor

| Tool | Description |
|------|-------------|
| `suggest_strategies` | Match strategies to your risk profile |
| `get_market_context` | Trend, volatility, support/resistance for a symbol |

## Prompt Templates

**Trading Assistant** — Start a conversation about your portfolio and positions. The AI calls `get_portfolio` and `get_positions` to ground its responses in your actual data.

**Strategy Builder** — Walk through creating, backtesting, and deploying a strategy. Pass an optional `goal` like "momentum strategy for ETH" to get focused suggestions.

**Portfolio Reviewer** — Deep analysis of your portfolio, positions, trade history, and performance. Identifies what's working, what isn't, and suggests improvements.

## Resources

MCP resources provide browsable data that AI clients can read directly:

| Resource | URI | Description |
|----------|-----|-------------|
| Portfolio | `tradestaq://portfolio` | Balances, positions, and active bots |
| Bots | `tradestaq://bots` | All bots with status and PnL |
| Strategies | `tradestaq://strategies` | Strategy catalog with ratings |

## Architecture

```
                    stdio                                    HTTPS
┌──────────────┐◄──────────►┐                  ┌────────────────►┌──────────────┐
│Claude Desktop│             │                  │                 │              │
│Cursor / CLI  │             │  tradestaq-mcp   │   Bearer JWT    │  TradeStaq   │
└──────────────┘             │  46 tools        │◄────────────────│  API         │
                             │  3 prompts       │                 │              │
┌──────────────┐  HTTP+SSE  │  3 resources      │                 └──────────────┘
│ Any MCP      │◄──────────►│                  │
│ client (web) │             └──────────────────┘
└──────────────┘
```

- **Two transports:** stdio (local, default) and HTTP+SSE (remote, `--http` flag)
- Hosted at `https://mcp.tradestaq.com/mcp` for remote clients
- JWT auth via OAuth PKCE or email/password login
- All tools return structured JSON with error contract
- Token auto-refresh when expiring within 1 hour

## Development

```sh
npm run dev        # watch mode with tsx
npm run build      # compile TypeScript
npm run lint       # type check without emitting
npm test           # run tests
npm start          # run server (stdio)
npm run start:http # run server (HTTP+SSE on port 3100)
```

### Releasing

```sh
npm run release:patch   # or release:minor / release:major
```

This bumps the version (and the `server.json` versions), files the CHANGELOG's
`[Unreleased]` notes under it, commits, tags `vX.Y.Z` and pushes. The tag triggers
`.github/workflows/publish.yml`:

1. **Approve the run.** The publish job waits in the `npm` environment for a maintainer's
   approval (Actions, then the run, then *Review deployments*).
2. It type-checks, tests and publishes to npm through trusted publishing (no npm token
   anywhere), with provenance.
3. It updates the listing on the official MCP Registry.

Then run the **Deploy MCP** workflow to update the hosted server at mcp.tradestaq.com.

## Error Handling

All tool errors return structured responses:

```json
{
  "error": {
    "code": "INSUFFICIENT_BALANCE",
    "message": "Human-readable description",
    "retryable": true,
    "retryAfterMs": 5000
  }
}
```

Error codes: `AUTH_EXPIRED`, `TIMEOUT`, `RATE_LIMITED`, `NETWORK_ERROR`, `HTTP_4xx`, `HTTP_5xx`.

## Security

- Credentials never enter AI conversation history
- OAuth PKCE flow with browser-based authentication
- Token stored with 0600 file permissions
- Localhost-only OAuth callbacks
- `deploy_bot`, `stop_bot`, `close_position`, and `follow_trader` are destructive operations (AI confirms with user)

## Links

- **Website:** [tradestaq.com](https://tradestaq.com)
- **Documentation:** [tradestaq.com/docs](https://tradestaq.com/docs)
- **MCP & AI trading tools:** [tradestaq.com/mcp](https://tradestaq.com/mcp)
- **Pricing:** [tradestaq.com/pricing](https://tradestaq.com/pricing)
- **npm package:** [@the-staq/tradestaq-mcp](https://www.npmjs.com/package/@the-staq/tradestaq-mcp)

## License

MIT

TDQS

B3.3/5.0

Scored across 34 tools

Disambiguation4/5

Most tools have clearly distinct purposes, with only minor overlap among auth-related tools (authenticate, login, set_token) and portfolio vs positions vs trade history. Descriptions are sufficiently detailed to resolve ambiguity.

Naming Consistency5/5

Tool names consistently follow the verb_noun pattern (e.g., close_position, create_strategy, list_bots). Only login/logout deviate, but that's standard for auth verbs. The pattern is predictable and uniform.

Tool Count3/5

34 tools is above the typical 3-15 range for a well-scoped server. While the domain is broad (strategy management, backtesting, bots, portfolio, copy trading), the number feels heavy and may overwhelm agents.

Completeness3/5

The tool surface covers core trading workflows but lacks update and delete operations for strategies and bots. Create and deploy are present, but modifications and deletions are absent, creating notable gaps.