Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add iuk-ink/binance-mcp-server --skill binance-tradergit clone --depth 1 https://github.com/iuk-ink/binance-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/iuk-ink/binance-mcp-server/binance-trader)<a href="https://agentmods.dev/skills/iuk-ink/binance-mcp-server/binance-trader"><img src="https://agentmods.dev/badge/skills/iuk-ink/binance-mcp-server/binance-trader/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/iuk-ink/binance-mcp-server/binance-trader"><img src="https://agentmods.dev/badge/skills/iuk-ink/binance-mcp-server/binance-trader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00113 | $0.02228 |
| Opus 5 | $0.00056 | $0.01114 |
| Sonnet 5 | $0.00023 | $0.00446 |
| Haiku 4.5 | $0.00011 | $0.00223 |
Grade A, and why
binance-trader scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Binance 期货交易指南
面向 AI 助手的 binance-mcp-server 使用知识。只覆盖工具描述装不下的内容(安装自检、工具选择、跨工具编排、安全纪律、错误恢复),参数约束与合法值一律以各工具自带描述为准,不在此复述。
前置条件(先读)
本手册涉及的全部工具来自 binance-mcp-server MCP 服务器(npm 包 @iuk-ink/binance-mcp-server)。只安装本 skill 而未接入该 MCP 时,任何工具调用都会失败——此时不要反复尝试工具或编造数据,应引导用户安装。
开始前自检:首次为本用户服务时,先确认工具可用——调用一次 market_ping(最轻量只读探测)或查看可用工具列表是否包含 market_* 系列:
- 探测成功 → 按后续章节正常工作
- 工具不存在 → 停止一切工具调用,向用户说明需安装 MCP 服务器,并给出以下配置(加入 MCP 客户端的
mcpServers配置后重启客户端):
{
"mcpServers": {
"binance": {
"command": "npx",
"args": ["-y", "@iuk-ink/binance-mcp-server"],
"env": {
"BINANCE_TESTNET": "true"
}
}
}
}
需要交易功能时在 env 补充 BINANCE_API_KEY 与 BINANCE_API_SECRET;默认测试网(虚拟金)零资金风险。
接入方式选择:本地单客户端用上面的 stdio 配置(command + args);远程部署 / 多客户端共享用下方 HTTP 配置。两种方式工具行为完全一致,仅客户端配置形态不同——按用户环境二选一即可。
{
"mcpServers": {
"binance": {
"type": "http",
"url": "http://<host>:3100/mcp"
}
}
}
远程部署变体:若服务器对外暴露并设了 MCP_HTTP_TOKEN,需在 HTTP 配置的 headers 中回传 Bearer 令牌("headers": { "Authorization": "Bearer <token>" })。
环境认知
| 事实 | 含义 |
|---|---|
| 默认连接测试网(虚拟金) | 未配置凭证即可全功能试用,交易操作零资金风险;切主网需 BINANCE_TESTNET=false + API 凭证 |
| 情绪端点仅主网注册 | OI 历史 / 多空比 / 主动买卖量 / 大户持仓 4 个工具在测试网不存在,属正常裁剪而非故障 |
| trading 域依赖凭证 | 无凭证时 21 个交易工具不注册(调用报 unknown tool 属正常),行情 / 指标 / 风险分析不受影响 |
| 指标返回条数 < limit 属正常 | 每个指标按自身预热需求跳过前若干根(如 limit=200 时 SMA(20) 返回 181 条),不是数据缺失 |
| 个别工具域整体缺失 | 若 market_* 存在但某域全缺:trading 缺 = 未配凭证;多域缺 = 用户的 MCP_TOOL_DOMAINS 环境变量过滤了域,提示用户检查该配置 |
工具选择树
行情查询——按轻重分流:
- 只要最新价 →
market_price;要最优买卖价 →market_book_ticker(比深度盘轻量得多) - 要盘口深度 / 大单分布 →
market_orderbook - 综合体检(推荐起手)→
market_overview:单次调用 = 行情 + 六指标 + 资金费率 + 盘口 - 跨期基差分析 →
market_continuous_klines(永续 / 当季 / 次季对比)
技术指标:
- 只要 1 个指标 → 对应
indicator_*单工具 - 要 2 个以上 →
indicator_multi(单次 K 线拉取计算多个指标,省网络往返) - 判断趋势转折 →
indicator_ma_cross(均线交叉)+indicator_divergence(RSI 背离)组合使用
交易查询:
- 订单详情 →
trading_get_order,orderId 与 clientOrderId 双渠道均可;改单 / 撤单后 orderId 不变、clientOrderId 保留,两种方式都能查到终态 - 持仓模式 →
trading_position_mode:不传参即纯查询,传dual才执行切换——仅需了解模式时切勿带参调用
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 131 lines · 113 tokens per session scan A 200d9d14a972
binance-trader is a skill published in the GitHub repository iuk-ink/binance-mcp-server (1 stars, last pushed 16d ago), licensed MIT. It adds 113 tokens to every session and 2,228 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…
trading-signal
Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…
hyperliquid
Hyperliquid L1 perps DEX (69% market share).
bridge
Cross-chain token transfers using Wormhole and CCTP.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.