dsh-plugin-xquant
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@dsh-plugin-xquantList available factors and explain how the momentum factor is calculated with a stock example."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
dsh-plugin-xquant
把 xquant 的量化研究 MCP 接入 DeepSeek Harness。安装一次,就能在 dsh Web 中查询因子、策略逻辑与历史数据。
研究工具,不提供具体买卖建议、个性化投资建议或市场预测。历史业绩不代表未来表现,投资有风险。
安装
1. 安装 dsh
npm install --global @deepseek-ai/dsh@0.1.0-rc.7
dsh --version如果提示 dsh: command not found,执行下面两行后重开终端:
echo 'export PATH="$(npm prefix -g)/bin:$PATH"' >> ~/.zshrc
exec zsh2. 安装 xquant 插件
先在 xquant 开发者中心 创建 API Key,再执行:
export XQUANT_API_KEY='xq_live_...'
dsh plugin --profile web add dsh-plugin-xquant启动 dsh Web:
dsh web插件默认连接 https://xquant.shop/xquant-mcp/mcp。不要填写已迁移的 /factor-mcp/ 路径。
Related MCP server: deepq-financial-toolkit
可做什么
查询可用因子及其定义;
计算已支持标的和时间窗口的因子时序;
浏览策略逻辑、历史绩效与历史信号的权限内信息;
让“小量”风格的研究指引把工具结果解释成更易读的研究结论。
示例问题:
动量因子通常怎样计算?先查 xquant 的因子定义,再用一个股票示例说明。帮我比较两个已公开策略的历史收益和回撤;不要给出买卖建议。配置私有或 staging 环境
仅需覆盖服务 origin;插件会固定补全 /xquant-mcp/mcp,从而避免误连旧路径:
export XQUANT_MCP_ORIGIN='https://staging.xquant.shop'
export XQUANT_API_KEY='xq_live_...'XQUANT_MCP_ORIGIN 必须是没有 path、query 或 hash 的 HTTP(S) origin,例如 https://mcp.example.com。它不是完整 MCP URL。
权限、计费与安全
API Key 只从 dsh 进程环境读取;插件不写入配置文件、不上传、不打印该值。
xquant 服务端是权限和合规的唯一边界。付费内容、近期调仓信号和管理员工具只会按当前账号权限返回;非管理员不会因安装插件而获得管理员工具。
插件不在本地计费。服务端只会按既有规则对成功的
compute_factor调用记录用量;MCP 握手、工具枚举和失败调用不应扣除因子计算额度。未设置
XQUANT_API_KEY时,请访问 开发者中心 获取 Key 后重启 dsh。
开发
pnpm install
pnpm test
pnpm run typecheck
pnpm run buildDeepSeek Harness 仍处于 developer preview。本包目前针对 dsh@0.1.0-rc.7 验证;升级 dsh 前请运行完整冒烟测试并阅读 release notes。
License
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityCmaintenanceAn MCP server that integrates the XTQuant quantitative trading platform with AI assistants, allowing AI to directly access and operate on trading data and functionality.8156MIT
- AlicenseCqualityDmaintenanceThe MCP provides comprehensive financial data and analytical tool support for AI large language models, specifically including the following five core data capabilities: Stock Analysis/ETF Analysis/Public Funds/News & Information/General Tools More Info: https://github.com/shenqingtech/deepq-finan44407ISC
- FlicenseNot gradedqualityDmaintenanceEnables quant research, strategy generation, backtesting, and paper trading from natural language prompts, integrating with AI agents via an MCP server.61
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to directly access quant research knowledge, including factor libraries, strategy backtesting, and research reports, through the MCP protocol.93MIT
Related MCP Connectors
Build, backtest, and deploy quantitative trading strategies from your AI agent.
The financial MCP for AI agents - 90+ financial tables, SEC filings, signals, alt-data.
Real SEC, 13F, insider, congress & macro data your AI agent can cite. Hosted MCP, 24 tools.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/codingDuan/dsh-plugin-xquant'
If you have feedback or need assistance with the MCP directory API, please join our Discord server