AlgoRover Research
Server Details
Discover trading strategies, run historical backtests, and inspect research reports.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- algorover/algorover-research
- GitHub Stars
- 1
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 16 tools
Tools map to distinct resource+action pairs, but a few near-neighbors invite misselection: prepare_backtest vs start_backtest and get_backtest vs get_backtest_result vs get_backtest_report_download rely on careful reading of the descriptions to differentiate. delete_backtest_result vs delete_research_data are also risky adjacent destructive tools, though scope differences are stated. Overall distinguishable with descriptions.
Uniform snake_case verb_noun pattern throughout (list_backtests, get_backtest_result, prepare_strategy, start_backtest). Verbs consistently reflect the action (get/list/delete/prepare/start/cancel/search), and resource names stay stable across prefixes. No mixed conventions.
16 tools is at the upper edge of the comfortable range but each maps to a real step in the strategy-discovery → prepare → run → inspect → cleanup lifecycle. A couple of retrieval variants (report download vs result) could arguably merge, so it's slightly heavy but justified.
Full lifecycle is covered: strategy search/get/prepare/download, backtest prepare/start/cancel/list/get/result/trades/report download/delete, plus profile, usage, and data deletion. Minor gaps: no update/rename of backtest metadata or batch operations, and no way to inspect presets independently, but core workflows have no dead ends.
Available Tools
16 toolscancel_backtestCDestructiveIdempotentInspect
请求取消本人回测。
Inputs: backtest_id (required), locale. Returns: data, error, schema_version
delete_backtest_resultBDestructiveIdempotentInspect
删除本人终态回测结果并撤销文件访问。
Inputs: backtest_id (required), locale. Returns: data, error, schema_version
delete_research_dataADestructiveIdempotentInspect
仅在用户明确要求时永久删除个人研究数据并撤销当前授权。删除期间暂停访问;完成后可使用同一账号重新登录授权,开始新的研究,旧数据不会恢复。
Inputs: confirmation (required), locale. Returns: data, error, schema_version
get_backtestCRead-onlyIdempotentInspect
查询本人回测任务的状态、错误和保留期限。
Inputs: backtest_id (required), locale. Returns: data, error, schema_version
get_backtest_report_downloadBRead-onlyIdempotentInspect
为本人已存在的报告文件生成短期下载地址。
Inputs: backtest_id (required), locale, artifact_kind. Returns: data, error, schema_version
get_backtest_resultBRead-onlyIdempotentInspect
读取本人已完成回测的真实指标、有限曲线和复现信息。
Inputs: backtest_id (required), locale, equity_max_points. Returns: data, error, schema_version
get_profileARead-onlyIdempotentInspect
读取当前已授权的 AlgoRover 账号资料。
Inputs: no named parameters. Returns: id, name, email
get_research_usageBRead-onlyIdempotentInspect
查询本人的运行中和排队任务数量。
Inputs: locale. Returns: data, error, schema_version
get_strategyBRead-onlyIdempotentInspect
读取公司已发布策略及其现有解析状态、预设和市场。
Inputs: slug (required), locale, version. Returns: data, error, schema_version
get_strategy_downloadBRead-onlyIdempotentInspect
取得确定版本的公开策略下载信息;不安装或执行文件。
Inputs: strategy_ref (required), locale. Returns: data, error, schema_version
list_backtestsBRead-onlyIdempotentInspect
分页列出本人的历史回测任务。
Inputs: limit, cursor, locale, status. Returns: data, error, schema_version
list_backtest_tradesBRead-onlyIdempotentInspect
分页读取本人已完成回测的成交明细。
Inputs: backtest_id (required), limit, cursor, locale. Returns: data, error, schema_version
prepare_backtestBRead-onlyIdempotentInspect
准备固定版本、预设和历史窗口,返回预览;不创建回测。
Inputs: days (required), venue (required), preset (required), strategy_ref (required), +1 more. Returns: data, error, schema_version
prepare_strategyBIdempotentInspect
为指定的已发布策略版本安排预设解析,不启动回测。
Inputs: strategy_ref (required), retry, locale. Returns: data, error, schema_version
search_strategiesBRead-onlyIdempotentInspect
打开 AlgoRover Research 内嵌策略目录,搜索公开策略并返回精确版本。含连字符的完整策略 slug 精确匹配,普通关键词按相关性搜索。首次目录显式传入会话语言 locale:中文用 zh-CN,英文用 en;用户指定语言时优先采用。后续详情和目录保持相同语言。
Inputs: sort, limit, query, cursor, +2 more. Returns: data, error, schema_version
start_backtestCIdempotentInspect
创建个人远端历史回测任务,返回任务标识。
Inputs: prepared_input (required), idempotency_key (required), preparation_ticket (required), locale. Returns: data, error, schema_version
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Mine, validate and paper-trade quantitative trading strategies. The engine runs on your machine.
Quant research, backtesting, marketplace subscriptions, editable forks, copy trading, and execution.
Build, backtest, and deploy quantitative trading strategies from your AI agent.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides tools to research crypto trading strategies via backtesting, walk-forward validation, and paper trading, with a deflated-Sharpe overfitting check. Enables natural-language-driven analysis and interpretation of strategy performance.2Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables quantitative trading research by providing tools to backtest strategies, list market datasets, review forward-test logs, and search previously rejected hypotheses, all through an MCP interface.MIT

panther-mcpofficial
AlicenseAqualityDmaintenanceEnables AI assistants to backtest trading strategies described in plain English, providing access to market data, technical indicators, and comprehensive performance reports.131MIT- FlicenseNot gradedqualityDmaintenanceEnables quant research, strategy development, backtesting, and paper trading through natural language prompts, integrated with 20+ AI agents.134-
Glama MCP Gateway
Add one secure layer between your agents and this server.