Spera MCP Server
Spera for Cursor
Spera for Cursor 将生产级的 Spera MCP 服务器及其可移植的代理技能打包成一个可安装的插件。它帮助用户创建和修改策略图、模块和自定义节点;运行精确版本回测;以及维护项目知识和制品文档。
功能
发现授权的 Spera 项目和制品。
创建、分支、编辑和编译策略。
创建和配置可复用模块。
创建、修补和编译结构化的自定义节点。
运行有限范围的快速和持久深度回测。
读取和更新项目知识,并附带版本安全的引用。
读取和更新策略、模块和自定义节点的文档。
该插件不部署实时交易机器人、管理交易所凭据或授权实时交易。回测结果是针对精确版本的历史证据,并非性能保证。
Related MCP server: qanat
连接
该插件通过 Streamable HTTP 连接到 https://api.spera.bot/mcp。首次使用时,Cursor 会打开 Spera 的 OAuth 授权流程。登录到 Spera,并仅批准同意屏幕中显示的作用域。完整的创作授权会暴露 31 个工具。
本地测试
将此仓库复制或链接到 Cursor 的本地插件目录:
~/.cursor/plugins/local/spera重启 Cursor 或运行 开发者:重新加载窗口,然后打开 自定义 并确认 Spera 的技能和 MCP 服务器均已列出。完成 OAuth 并在测试写入工作流之前验证 spera_context_get 报告了预期的作用域。
仓库检查使用 Node.js 20 或更高版本,且无第三方依赖:
npm test
npm run test:live
npm run validate:submissiontest:live 验证公共 MCP OAuth 发现链。validate:submission 额外要求在提交市场前获得批准的开源许可证。
数据处理、隐私与支持
数据处理:DATA_HANDLING.md
切勿在提示、问题或支持请求中包含访问令牌、交易所凭据或私钥。
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Quant research, backtesting, marketplace subscriptions, editable forks, copy trading, and execution.
Build, backtest, and deploy quantitative trading strategies from your AI agent.
Cloud platform for asset research and investment allocation models, saving code, runs and outputs.
Design trading strategies with your AI and open them in a visual no-code Strategy Builder.
Related MCP Servers
- FlicenseAqualityCmaintenanceEnables agents to generate alpha signals, retrieve market snapshots, compute portfolio risk, validate and submit paper orders, and trigger a kill switch, all under deterministic pre-trade risk controls and audit logging.5-

qanatofficial
AlicenseNot gradedqualityBmaintenanceEnables agents to inspect, plan, run, and backtest alpha pipelines expressed as DAGs, with tools for table discovery, lineage, backtests, reports, and workflow authoring.240 PyPI332MIT- AlicenseNot gradedqualityCmaintenanceEnables AI agents to run a full quant research workflow over MCP: pulling data, authoring and backtesting strategies, running statistical validation and risk checks, and recording findings for future sessions.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables users to prepare and validate market data, launch and control backtests, and retrieve results, causal explanations, and self-contained reports through stdio tools. It also supports polling or canceling jobs and running sweep, walk-forward, factor, and study research workflows with bounded pagination and reproducible artifacts.MIT