btse-mcp
An MCP server for the BTSE Futures API that allows AI agents to query market data, manage positions, and execute trades using natural language. It supports both live and testnet accounts with features for order management, leverage adjustment, and wallet balance tracking.
README
btse-mcp
MCP server for the BTSE Futures API. Enables AI agents (Claude Desktop, Cursor, LangChain) to query market data, manage positions, and place orders on BTSE via natural language.
Prerequisites
- Python 3.11 or higher — check with
python --version - pip — check with
pip --version - A BTSE account (testnet or live)
Multiple Python versions (Anaconda etc): use the full path explicitly:
/usr/local/bin/python3.14 -m pip install -e . /Library/Frameworks/Python.framework/Versions/3.14/bin/btse-mcp --helpUse that same full path in the Claude Desktop config (Step 4).
Step 1 — Get API keys from BTSE
Testnet (recommended first)
- Register at https://testnet.btse.io
- Go to Account → API tab → New API
- Save the API Key and Passphrase — the passphrase is shown only once and is your
api_secret - Set permissions: Read + Trading (add Transfer if needed)
Live
Same steps at https://btse.com
Step 2 — Install
# Clone the repo
git clone https://github.com/xbotlive/btse-mcp.git
cd btse-mcp
# Install — adds `btse-mcp` command to your PATH
pip install -e .
# Verify
btse-mcp --help
Virtualenv users: if
btse-mcpis not found after install, use the full path:
- macOS/Linux:
~/.venv/bin/btse-mcp- Windows:
~\.venv\Scripts\btse-mcp.exeYou will need this full path in the Claude Desktop config (Step 4).
Step 3 — Configure accounts
# Add a testnet account
btse-mcp config --account-id testnet
# Prompts:
# API Key → paste your API key
# API Secret → paste your passphrase (input is hidden)
# Use testnet? [y/N] → y
# Verify the connection — should print BTC-PERP last price
btse-mcp test testnet
# Add your live account when ready
btse-mcp config --account-id main
# Same prompts — answer 'n' to testnet
# See all configured accounts
btse-mcp list
Credentials are stored encrypted at ~/.config/btse-mcp/accounts.enc.
Unified Futures Wallet: If your BTSE account has been upgraded to the Unified Futures Wallet (all accounts from late 2024 onwards), account endpoints automatically use the v2.2 API. No action needed.
Step 4 — Connect to Claude Desktop
Find the config file for your OS:
| OS | Path |
|---|---|
| macOS | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Windows | %APPDATA%\Claude\claude_desktop_config.json |
| Linux | ~/.config/Claude/claude_desktop_config.json |
Open the file (create it if it doesn't exist) and add:
{
"mcpServers": {
"btse": {
"command": "btse-mcp",
"args": ["start"]
}
}
}
Virtualenv users: replace
"btse-mcp"with the full path, e.g.:"command": "/Users/yourname/.venv/bin/btse-mcp"
Restart Claude Desktop. Open a new chat — you should see a tools icon (🔧) in the input bar.
Test it:
"What is the BTC-PERP mark price on BTSE using account testnet?"
Step 5 — Connect to Cursor
Open Cursor → Settings → MCP → Add Server and enter:
{
"name": "btse",
"command": "btse-mcp",
"args": ["start"]
}
Then use natural language in Cursor chat:
"Show my open BTSE positions" "Place a limit buy on BTC-PERP at 60000 size 1 using account testnet"
Alternative: run without installing
# From the repo root, no pip install required
python -m btse_mcp start
Tool list
| Tool | Description |
|---|---|
btse_get_market_summary |
Market summary for one or all symbols |
btse_get_price |
Mark / index / last price |
btse_get_orderbook |
L2 orderbook snapshot |
btse_get_trades |
Recent public trade fills |
btse_get_ohlcv |
OHLCV candlestick data |
btse_get_funding_history |
Historical funding rates |
btse_get_wallet_balance |
Futures wallet balance |
btse_get_positions |
Open positions |
btse_get_account_fees |
Maker / taker fee rates |
btse_get_leverage |
Current leverage for a market |
btse_create_order |
Place LIMIT / MARKET / OCO order (supports TP/SL) |
btse_cancel_order |
Cancel by order ID, or cancel all for a symbol |
btse_get_open_orders |
List open orders |
btse_get_order |
Single order detail |
btse_get_trade_history |
User trade history |
btse_amend_order |
Amend price / size / trigger price |
btse_close_position |
Close position at market or limit |
btse_set_leverage |
Set leverage (isolated or cross) |
btse_get_risk_limit |
Get risk limit tier |
All tools accept an optional account_id parameter (defaults to "default").
Pass "account_id": "testnet" to route to your testnet account.
Multi-account usage
btse-mcp list # list all configured accounts
btse-mcp test main # test a specific account
In prompts, specify the account explicitly:
"Using account testnet, show my BTC-PERP position"
Symbol naming
Use new-style perpetual names: BTC-PERP, ETH-PERP, SOL-PERP, etc.
Auth
BTSE uses HMAC-SHA384. The signature is:
HMAC-SHA384(api_secret, url_path + nonce + request_body)
Sent via headers: request-api, request-nonce, request-sign.
See docs/integration.md for full details and worked examples.
Running tests
pip install pytest
pytest -v
Auth signature tests run against the worked examples in the BTSE docs — no live API connection needed.
Troubleshooting
| Problem | Fix |
|---|---|
btse-mcp: command not found |
Use full path or activate your virtualenv |
401 Unauthorized |
Check API key and secret are copied correctly |
Connection failed |
Confirm testnet flag matches the account you created on |
| Tools icon missing in Claude Desktop | Check JSON syntax in config file, restart Claude Desktop |
ModuleNotFoundError: mcp |
Run pip install -e . again from the repo root |
33000001: Unsupported API |
Your account uses the Unified Futures Wallet — the server auto-retries on v2.2, restart Claude Desktop |
btse-mcp test works but account tools fail |
Restart Claude Desktop after any config or code change |
Disclaimer
Futures trading involves significant risk of loss. Always test on testnet before using live credentials.
Never commit API keys to version control — they are stored encrypted locally and excluded via .gitignore.
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。