# stagenth · 数据工具箱 (remote · stagenth.com)

Query, join, profile, clean and convert CSV/JSON/Parquet with server-side DuckDB over MCP.

- Trust score: 66/100 (medium)
- Change this week: +5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `stagenth.com`: 66/100 (this document), [markdown](https://verifymcp.io/servers/com-stagenth-data-kit/mcp-data-kit.md), [page](https://verifymcp.io/servers/com-stagenth-data-kit/mcp-data-kit)

## Channel facts

- Endpoint: `https://stagenth.com/mcp/data-kit/`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 6 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 58/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1599 tokens (~266/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http com-stagenth-data-kit https://stagenth.com/mcp/data-kit/
```

### Codex

```toml
[mcp_servers.com-stagenth-data-kit]
url = "https://stagenth.com/mcp/data-kit/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-stagenth-data-kit": {
      "type": "remote",
      "url": "https://stagenth.com/mcp/data-kit/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-stagenth-data-kit --url https://stagenth.com/mcp/data-kit/ --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-stagenth-data-kit:
    url: "https://stagenth.com/mcp/data-kit/"
```

### Other

```json
{
  "mcpServers": {
    "com-stagenth-data-kit": {
      "type": "http",
      "url": "https://stagenth.com/mcp/data-kit/"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 64, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 63, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 61, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 60)

First indexed and scored.

## MCP tools (6)

### `data_inspect` (~166 tokens)

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。

Input parameters:

- `data_base64`: 数据文件内容 base64（与 file_id 二选一，适合未上传的临时数据）
- `file_id`: 已上传到文件中转站的数据文件 ID（与 data_base64 二选一）
- `fmt`: 格式 csv/tsv/json/ndjson/parquet；缺省按内容自动识别
- `preview_rows` (integer): 预览前 N 行

### `data_query` (~568 tokens)

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[]}。

Input parameters:

- `agg`: 聚合方式 sum/avg/count/min/max/median（默认 sum；count=数每组行数、无需 measures）
- `columns`: 明细模式：只返回这些列；缺省返回全部列
- `data_base64`: 数据文件内容 base64（与 file_id 二选一）
- `descending` (boolean): 降序排序（取 Top-N 常用 true）
- `file_id`: 已上传的数据文件 ID（与 data_base64 二选一）
- `filters`: 行过滤条件（AND 组合），每项 {column, op, value}。op 可选：eq/ne/gt/ge/lt/le/contains/in/notnull/isnull。例：[{"column":"状态","op":"eq","value":"失败"},{"column":"金额","op":"ge","value":1000}]
- `fmt`: 格式 csv/tsv/json/ndjson/parquet；缺省自动识别
- `group_by`: 分组维度列。给了就进聚合模式：按这些列分组，对 measures 求 agg
- `limit`: 最多返回多少行（取前 N / Top-N）；硬上限 1000
- `measures`: 聚合模式：要统计的数值列；缺省=所有非分组的数值列
- `sort_by`: 按哪一列排序（可为分组后的 measure 或 count 列）
- `sql`: 只读 SQL，表名固定为 t。例：SELECT 地区, sum(金额) AS 合计 FROM t GROUP BY 地区 ORDER BY 合计 DESC LIMIT 10。仅允许单条 SELECT/WITH，禁止读文件/建表/联网。给了 sql 就忽略下面的结构化参数。

### `data_profile` (~151 tokens)

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[]}。

Input parameters:

- `data_base64`: 数据文件内容 base64（与 file_id 二选一）
- `file_id`: 已上传的数据文件 ID（与 data_base64 二选一）
- `fmt`: 格式 csv/tsv/json/ndjson/parquet；缺省自动识别

### `data_convert` (~162 tokens)

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。

Input parameters:

- `data_base64`: 数据文件内容 base64（与 file_id 二选一）
- `file_id`: 已上传的数据文件 ID（与 data_base64 二选一）
- `fmt`: 源格式 csv/tsv/json/ndjson/parquet；缺省自动识别
- `to` (string, required): 目标格式：csv / json / ndjson / parquet / xlsx

### `data_join` (~245 tokens)

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。

Input parameters:

- `columns`: 只返回这些列；缺省返回全部
- `data_base64_a`: 数据 A 内容 base64
- `data_base64_b`: 数据 B 内容 base64
- `file_id_a`: 数据 A 的文件 ID（与 data_base64_a 二选一）
- `file_id_b`: 数据 B 的文件 ID（与 data_base64_b 二选一）
- `fmt_a`: A 格式 csv/tsv/json/ndjson/parquet；缺省自动识别
- `fmt_b`: B 格式；缺省自动识别
- `how` (string): 连接方式 inner / left
- `limit`: 最多返回行数；硬上限 1000
- `on` (array, required): 连接列名（两份数据中都存在，最多 8 个）

### `data_clean` (~181 tokens)

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）。

Input parameters:

- `data_base64`: 数据内容 base64
- `dedupe` (boolean): 整行去重
- `drop_empty_cols` (boolean): 删除全空列
- `drop_empty_rows` (boolean): 删除全空行
- `file_id`: 数据文件 ID（与 data_base64 二选一）
- `fmt`: 源格式 csv/tsv/json/ndjson/parquet；缺省自动识别
- `to` (string): 输出格式 csv/json/ndjson/parquet/xlsx，默认 csv
- `trim_strings` (boolean): 字符串去首尾空白，空串归 NULL

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-stagenth-data-kit/mcp-data-kit#diagnostics

## Score history

- 2026-08-03: 66
- 2026-08-02: 65
- 2026-08-01: 65
- 2026-07-31: 64
- 2026-07-30: 63
- 2026-07-29: 62
- 2026-07-28: 62
- 2026-07-27: 61
- 2026-07-26: 60

## Links

- Remote endpoint: https://stagenth.com/mcp/data-kit/
- Authorisation metadata: https://stagenth.com/.well-known/oauth-protected-resource/mcp/data-kit
- Changelog RSS feed: https://verifymcp.io/servers/com-stagenth-data-kit/mcp-data-kit/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-stagenth-data-kit/mcp-data-kit/changelog.json
- HTML version of this page: https://verifymcp.io/servers/com-stagenth-data-kit/mcp-data-kit