stockmarketscan/mcp-server
OfficialStockMarketScan MCP 服务器
股票筛选、图表形态、期权流和信号——18 个用于美股研究的工具,集成在你的 LLM 客户端中。
服务器 URL:
https://mcp.stockmarketscan.com/mcp传输协议: HTTP/SSE (Server-Sent Events)
认证: BYOK — 将你的个人
sms_*API 密钥作为X-API-Key请求头传递套餐: 需要 stockmarketscan.com 的 Basic 或 Pro 套餐。期权流工具需要“期权流”附加组件。
获取 API 密钥: stockmarketscan.com/settings
完整安装指南及示例: stockmarketscan.com/mcp
你将获得什么 — 18 个工具
分类 | 工具 |
筛选器 (3) |
|
图表形态 (2) |
|
期权流 (4) |
|
股票信息 (2) |
|
综合 (2) |
|
市场环境 (3) |
|
教育 (1) |
|
此外还有用于存活检查的 ping。
安装 — Claude Desktop
编辑 claude_desktop_config.json:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"stockmarketscan": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.stockmarketscan.com/mcp"],
"headers": {
"X-API-Key": "sms_your_key_here"
}
}
}
}重启 Claude Desktop。你应该能在工具选择器中看到 stockmarketscan。
安装 — Cursor
设置 → 功能 → Model Context Protocol → 添加新的 MCP 服务器:
{
"name": "stockmarketscan",
"url": "https://mcp.stockmarketscan.com/mcp",
"headers": {
"X-API-Key": "sms_your_key_here"
}
}安装 — Continue (VS Code / JetBrains)
编辑 ~/.continue/config.json:
{
"experimental": {
"modelContextProtocolServers": [
{
"transport": {
"type": "sse",
"url": "https://mcp.stockmarketscan.com/mcp",
"headers": {
"X-API-Key": "sms_your_key_here"
}
}
}
]
}
}示例提示词
服务器连接后,直接在 Claude Desktop 或 Cursor 中输入以下内容:
"Which stocks appear in both hot-prospects and golden-cross today?"
"Show me AMD's options flow history for the last 30 days."
"Find hot-prospects that are forming a cup and handle pattern."
"Build a full stock report for NVDA — screeners, patterns, options flow, market context."
"What are today's strongest bullish options flow signals?"
"Which contracts traded today at vol/OI > 3 with over $1M premium?"
认证工作原理 (BYOK)
MCP 服务器不持有自己的 API 密钥。每个客户端都会传递你的个人 sms_* 密钥,服务器在每个会话中验证一次,然后代表你将工具调用代理到 api/v1/*。你可以掌控速率限制和配额,并随时在 设置 中轮换密钥。
速率限制
套餐 | 每分钟 | 每天 | 期权流 |
免费 | — | — | — |
Basic | 15 | 500 | — |
Pro | 30 | 2,000 | ✓ |
支持
从源码运行
git clone https://github.com/stockmarketscan/mcp-server.git
cd mcp-server
npm install
STOCKMARKETSCAN_API_KEY=sms_your_key_here npm run dev # stdio (for Claude Desktop local)
npm run dev:http # HTTP/SSE on :3333Docker
docker build -t stockmarketscan-mcp .
docker run -p 3333:3333 -e MCP_TRANSPORT=http stockmarketscan-mcp容器监听 $PORT (Railway) 或 $MCP_PORT (本地)。将你的 MCP 客户端指向 http://localhost:3333/mcp 并传递你的 X-API-Key 请求头。
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/stockmarketscan/mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server