当用户希望查询数据集数据的时候，将数据集数据下载到CSV文件后，用户可以进行进一步的分析和处理。需要指定数据集名称、保存路径、时间范围和采样间隔。 ⚠️ 使用建议： - 当用户查询 7 天以上的数据：建议分批下载或使用更大的采样间隔（如 60 分钟） - 大范围查询会自动分块处理，避免超时 📅 时间格式说明： 1. 日期格式 "YYYY-MM-DD"（前包含后包含）： - 示例：start="2025-01-01", end="2025-01-02" - 结果：包含 1月1日 和 1月2日 的完整数据 - 实际查询范围：2025-01-01 00:00:00 ~ 2025-01-03 ...
AI agents call download_dataset to retrieve information from Xmo Data without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
end | string | Yes | 结束时间（必需）。格式支持 "YYYY-MM-DD HH:MM:SS" 或 "YYYY-MM-DD" |
start | string | Yes | 开始时间（必需）。格式支持 "YYYY-MM-DD HH:MM:SS" 或 "YYYY-MM-DD" |
interval | number | — | 采样间隔（分钟），默认为15分钟。例如：15表示15分钟间隔，60表示1小时间隔。 |
file_path | string | Yes | CSV文件的保存路径（必需）。建议使用当前工作目录，例如：'./data.csv' |
dataset_name | string | Yes | 要下载的数据集名称（必需） |
Parameters from the server's own tool schema.
This tool retrieves and exports data in a read-only manner. It queries a dataset and outputs it to a file format without modifying the underlying data, triggering external operations, or causing destructive changes. The parameters control data filtering (time range, sampling) but not mutation.
From the tool's definition Tool name: 'download_dataset'; description states it 'downloads dataset data to CSV file' for 'further analysis and processing' with parameters for dataset name, save path, time range, and sampling interval.
Risk signalsAccepts file system path (file_path)
Attacks that exploit this kind of access
当用户希望查询数据集数据的时候，将数据集数据下载到CSV文件后，用户可以进行进一步的分析和处理。需要指定数据集名称、保存路径、时间范围和采样间隔。 ⚠️ 使用建议： - 当用户查询 7 天以上的数据：建议分批下载或使用更大的采样间隔（如 60 分钟） - 大范围查询会自动分块处理，避免超时 📅 时间格式说明： 1. 日期格式 "YYYY-MM-DD"（前包含后包含）： - 示例：start="2025-01-01", end="2025-01-02" - 结果：包含 1月1日 和 1月2日 的完整数据 - 实际查询范围：2025-01-01 00:00:00 ~ 2025-01-03 00:00:00（自动转换） 2. 时间格式 "YYYY-MM-DD HH:MM:SS"（前开后闭）： - 示例：start="2025-01-01 00:00:00", end="2025-01-02 00:00:00", interval=15 - 结果：第一个数据点是 2025-01-01 00:15:00，最后一个是 2025-01-02 00:00:00 - 说明：不包含起始时间点，包含结束时间点. It is categorised as a Read tool in the Xmo Data MCP Server, which means it retrieves data without modifying state.
download_dataset accepts 5 parameters: end, start, interval, file_path, dataset_name. Required: end, start, file_path, dataset_name. The full parameter table on this page comes from the server's own tool schema.
Register the Xmo Data MCP server in PolicyLayer and add a rule for download_dataset: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Xmo Data. Nothing to install.
download_dataset is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the download_dataset rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for download_dataset. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
download_dataset is provided by the Xmo Data MCP server (xmo-data-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
download_dataset is one line of Xmo Data's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →