qjtrader-mcp
MCP server for QJ Trader AI Trading APIs, enabling LLMs to watch live Canadian market data and place simulated orders.
README
qjtrader-mcp
Model Context Protocol server for the QJ Trader AI Trading APIs. Point your LLM at your QJ credential and it can watch live Canadian market data and place simulated orders — no code, no manual API testing.
Built on the official qjtrader Python SDK. Talk to
it from Claude Code, Claude Desktop, or any MCP-capable client:
"Subscribe to CA:RY and MX:CRAU26, show me the books, then buy 1 CRAU26 at 97 in the sandbox and tell me the fill."
Safety model — AI trades simulated by default
Order-mutating tools (place_order, cancel_order, replace_order, cancel_all) run against a
sandbox credential by default and return simulated fills. A live credential is refused
unless you explicitly opt in. The server never sniffs this off the wire (the protocol doesn't
expose it) — you declare it:
QJ_ENV |
Read tools (quotes/depth/status) | Order tools |
|---|---|---|
sandbox |
✅ | ✅ simulated |
live |
✅ | ⛔ unless QJ_MCP_ALLOW_LIVE=1 |
| (unset) | ✅ | ⛔ (fail-safe: unknown is treated as live) |
Every tool result is prefixed with an environment tag ([SANDBOX] / [LIVE — REAL MONEY] /
[ENV UNKNOWN]), and order quantity is capped client-side by QJ_MCP_MAX_QTY (default 25).
Install
Get a free sandbox credential (no approval) at console.qjtrader.ai.
Once published to PyPI, the zero-install path is:
uvx qjtrader-mcp # or: pipx run qjtrader-mcp
Until then (or for local development against the SDK checkout):
# from the qjtrader-mcp/ directory, with the qjtrader-python sibling checked out:
uv sync && uv run qjtrader-mcp # uv resolves qjtrader from ../qjtrader-python
# — or with pip —
pip install -e ../qjtrader-python -e .
qjtrader-mcp
Configure your client
Claude Code
claude mcp add qjtrader -- uvx qjtrader-mcp
# then set the credential + environment for the server:
claude mcp add qjtrader \
-e QJ_CLIENT_ID=your-client-id \
-e QJ_CLIENT_SECRET=your-client-secret \
-e QJ_ENV=sandbox \
-- uvx qjtrader-mcp
Claude Desktop / generic stdio
Add to your MCP config (claude_desktop_config.json or equivalent):
{
"mcpServers": {
"qjtrader": {
"command": "uvx",
"args": ["qjtrader-mcp"],
"env": {
"QJ_CLIENT_ID": "your-client-id",
"QJ_CLIENT_SECRET": "your-client-secret",
"QJ_ENV": "sandbox"
}
}
}
}
The console's "Connect your AI" panel generates these blocks pre-filled, including
QJ_ENV=sandbox.
Tools
| Tool | Kind | Description |
|---|---|---|
session_info |
read | Environment, whether order actions are allowed, endpoints, authenticated user. Call first. |
get_quote |
read | Top-of-book (best bid/ask) for one or more symbols |
get_depth |
read | Level-2 order book for a symbol (venue-tagged on consolidated books) |
watch |
read | Sample the live stream for a bounded window; returns a digest + last messages |
list_orders |
read | Open orders + session state |
place_order |
write | Submit a limit order and wait for a terminal state |
cancel_order |
write | Cancel a working order by cid |
replace_order |
write | Amend a working order's qty/price |
cancel_all |
write | Cancel every working order (kill switch) |
explain_symbol |
util | Parse/explain a symbol (prefix + root + venue), offline |
read_events |
read | Order journal — cross-order event history; post-trade analysis & strategy debugging |
get_history |
read | Historical OHLCV bars (1s/1m); sandbox = deterministic synthetic days |
get_stats |
read | Server digest for a symbol: VWAP, spread, volume, realized vol (a digest, not a dump) |
get_chain |
read | Options chain snapshot for an underlying/expiry (latest or historical) |
compare |
read | Rank a digest metric (vwap/volume/realized_vol/spread_mean) across symbols |
The read_*/get_* research tools make the LLM a quant developer: analyse the
market and debug the strategy it wrote, without touching the production order path.
Configuration reference
| Env var | Purpose | Default |
|---|---|---|
QJ_CLIENT_ID / QJ_CLIENT_SECRET |
credential | — (required) |
QJ_ENV |
sandbox | live — declares the environment |
unset → treated as live |
QJ_MCP_ALLOW_LIVE |
set 1 to authorize live order actions |
off |
QJ_MCP_MAX_QTY |
client-side max order quantity | 25 |
QJ_DATA_HOST / QJ_ORDERS_HOST |
endpoint overrides | public QJ hosts |
QJ_CA_FILE |
pin a CA/cert (pilot order endpoint) | none |
License
Apache-2.0. See LICENSE.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。