data_csv_analyze
Analyze CSV data to output column information, row count, and statistical summaries of numeric columns.
Instructions
分析 CSV 数据，输出列信息、行数、数值列统计等摘要。
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| csv_text | Yes | CSV 文本内容 | |
| delimiter | No | 分隔符（默认逗号） | , |
| max_rows | No | 预览行数（默认 5） |
Implementation Reference
- The actual handler function `_csv_analyze` that implements the data_csv_analyze tool logic. Parses CSV with csv.DictReader, computes row/column stats, prints a Markdown preview, and calculates numerical column statistics (min/max/avg).
def _csv_analyze(args: dict) -> list[types.TextContent]: csv_text = args["csv_text"] delimiter = args.get("delimiter", ",") max_rows = int(args.get("max_rows", 5)) reader = csv.DictReader(io.StringIO(csv_text), delimiter=delimiter) rows = list(reader) if not rows: return [types.TextContent(type="text", text="❌ CSV 为空或格式错误")] headers = list(rows[0].keys()) lines = [ "📊 CSV 分析\n", f"总行数: {len(rows)}", f"列数: {len(headers)}", f"列名: {', '.join(headers)}\n", f"**前 {min(max_rows, len(rows))} 行预览:**", ] # Markdown 表格预览 lines.append("| " + " | ".join(headers) + " |") lines.append("| " + " | ".join(["---"] * len(headers)) + " |") for row in rows[:max_rows]: lines.append("| " + " | ".join(str(row.get(h, "")) for h in headers) + " |") # 数值列统计 num_stats = [] for h in headers: vals = [] for row in rows: try: vals.append(float(row.get(h, ""))) except (ValueError, TypeError): pass if len(vals) > len(rows) * 0.5: # 超过一半是数值 num_stats.append( f" {h}: min={min(vals):.2f} max={max(vals):.2f} " f"avg={sum(vals)/len(vals):.2f}" ) if num_stats: lines.append("\n**数值列统计:**") lines.extend(num_stats) return [types.TextContent(type="text", text="\n".join(lines))] - Tool registration with schema definition for data_csv_analyze: defines name, description, and inputSchema with parameters csv_text (required), delimiter (default ','), and max_rows (default 5).
types.Tool( name="data_csv_analyze", description="分析 CSV 数据，输出列信息、行数、数值列统计等摘要。", inputSchema={ "type": "object", "properties": { "csv_text": {"type": "string", "description": "CSV 文本内容"}, "delimiter": { "type": "string", "description": "分隔符（默认逗号）", "default": ",", }, "max_rows": { "type": "integer", "description": "预览行数（默认 5）", "default": 5, }, }, "required": ["csv_text"], }, - src/onion_mcp_server/tools/data.py:17-96 (registration)The DATA_TOOLS list containing all data tools including data_csv_analyze (line 34-49). This list is exported via tools/__init__.py and registered in server.py line 43 and lines 56-57.
DATA_TOOLS: list[types.Tool] = [ types.Tool( name="data_json_query", description=( "用简单路径表达式查询 JSON 数据。\n" "路径语法: 用 . 分隔键名，用 [N] 访问数组元素。\n" "示例: 'users[0].name' 'data.items[*].id'" ), inputSchema={ "type": "object", "properties": { "json_text": {"type": "string", "description": "JSON 字符串"}, "path": {"type": "string", "description": "查询路径，如 users[0].name"}, }, "required": ["json_text", "path"], }, ), types.Tool( name="data_csv_analyze", description="分析 CSV 数据，输出列信息、行数、数值列统计等摘要。", inputSchema={ "type": "object", "properties": { "csv_text": {"type": "string", "description": "CSV 文本内容"}, "delimiter": { "type": "string", "description": "分隔符（默认逗号）", "default": ",", }, "max_rows": { "type": "integer", "description": "预览行数（默认 5）", "default": 5, }, }, "required": ["csv_text"], }, ), types.Tool( name="data_table_format", description="将 JSON 数组数据格式化为 Markdown 表格。", inputSchema={ "type": "object", "properties": { "data": { "type": "string", "description": "JSON 数组字符串，每个元素为一行数据（对象或数组）", }, "headers": { "type": "array", "items": {"type": "string"}, "description": "表头列表（留空则自动从数据推断）", "default": [], }, "align": { "type": "string", "description": "对齐方式: left / center / right（默认 left）", "enum": ["left", "center", "right"], "default": "left", }, }, "required": ["data"], }, ), types.Tool( name="data_convert", description="在 JSON、CSV、YAML、TOML 格式之间互相转换。", inputSchema={ "type": "object", "properties": { "text": {"type": "string", "description": "源数据文本"}, "from_format": { "type": "string", "enum": ["json", "csv", "yaml", "toml"], "description": "源格式", }, "to_format": { "type": "string", "enum": ["json", "csv", "yaml", "toml"], "description": "目标格式", }, }, "required": ["text", "from_format", "to_format"], }, ), ] - src/onion_mcp_server/server.py:56-61 (registration)Server registration: maps all DATA_TOOLS names to the handle_data dispatcher, which routes data_csv_analyze to the _csv_analyze handler via the handlers dict at data.py line 102.
for _t in DATA_TOOLS: _HANDLERS[_t.name] = handle_data for _t in WEB_TOOLS: _HANDLERS[_t.name] = handle_web for _t in SYSTEM_TOOLS: _HANDLERS[_t.name] = handle_system - The handle_data dispatcher function that routes tool names to handler functions. Maps 'data_csv_analyze' to _csv_analyze at line 102.
async def handle_data(name: str, arguments: dict) -> list[types.TextContent]: handlers = { "data_json_query": _json_query, "data_csv_analyze": _csv_analyze, "data_table_format": _table_format, "data_convert": _data_convert, } fn = handlers.get(name) if fn is None: raise ValueError(f"未知 data 工具: {name}") return fn(arguments)