mcp server
stagenth · 数据工具箱
Query, join, profile, clean and convert CSV/JSON/Parquet with server-side DuckDB over MCP.
Description as published by the maintainer. Source
- version 1.1.0
- active
active — Registry entry last updated 2026-07-05.
What this server can do
6 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
data_clean(to, fmt, dedupe, file_id, data_base64, trim_strings, drop_empty_cols, drop_empty_rows)- 一步清洗脏数据：去重 / 去空白 / 删全空行列，产物落文件中转站并返清洗统计（1 credit/次）。
data_convert(to, fmt, file_id, data_base64)- 把数据文件转成另一种格式（csv/json/ndjson/parquet/xlsx），产物存文件中转站返下载 URL（1 credit/次）。 典型：把大 CSV 转 parquet 便于后续分析、或把 JSON 日志转 xlsx 给人看。失败自动退款。 Required: to.
data_inspect(fmt, file_id, data_base64, preview_rows)- 查看数据文件结构：列名/类型/行数/每列非空数 + 前 N 行预览。免费(0 credit)。 支持 CSV/TSV/JSON/NDJSON/Parquet。取数(data_query)前先调它看清有哪些列、哪些是数值。
data_join(on, how, fmt_a, fmt_b, limit, columns, file_id_a, file_id_b, data_base64_a, data_base64_b)- 两份数据文件按共同列连接（如 订单表×客户表），返回实际数据行 JSON（1 credit/次）。 跨文件对齐是单文件 data_query 做不到的；DuckDB 引擎、锁死文件/网络访问。失败自动退款。 Required: on.
data_profile(fmt, file_id, data_base64)- 数据画像：每列类型/去重近似数/空值率 + 数值列 min/max/avg/std/分位数（1 credit/次）。 相当于 pandas df.describe()——AI 拿它一眼看清整份数据的分布与质量。失败自动退款。 返回 {ok, format, n_rows, n_cols, profile[]}。
data_query(agg, fmt, sql, limit, columns, file_id, filters, sort_by, group_by, measures, descending, data_base64)- 查询 / 过滤 / 分组聚合数据文件，返回**实际数据行（JSON）**供 AI 直接分析（1 credit/次）。 支持 CSV/TSV/JSON/NDJSON/Parquet，两种用法： · 原始 SQL（表名固定 t）：sql="SELECT 商品, sum(销量) s FROM t GROUP BY 商品 ORDER BY s DESC LIMIT 5" · 结构化（不用写 SQL）：group_by=["地区"], measures=["销售额"], agg="sum", sort_by="销售额", descending=true, limit=10 SQL 仅允许单条只读 SELECT/WITH，禁止读文件/建表/联网。结果硬上限 1000 行，超出置 truncated=True。失败自动退款。 返回 {ok, format, mode, columns, total_rows, returned_rows, truncated, rows[]}。
Last successful function declaration observed on . Source: https://stagenth.com/mcp/data-kit/. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://stagenth.com/mcp/data-kit/.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| Latest published version | 1.1.0 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-07-05 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| First listed in the MCP Registry | 2026-07-05 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| mcp tools declared | 6 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | stagenth.com | |
| mcp endpoint status | ok | The server listed 6 functions when asked. | as of probe | stagenth.com |
Where to get it
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json