Skip to main content
Glama
liqiongyu

Xueqiu MCP

by liqiongyu

capital_flow

Retrieve real-time capital inflow and outflow data for Chinese stocks, providing minute-by-minute updates on stock code performance.

Instructions

获取当日资金流如流出数据,每分钟数据

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
stock_codeNoSZ000002

Implementation Reference

  • main.py:106-110 (handler)
    The handler function for the 'capital_flow' MCP tool. It calls pysnowball's ball.capital_flow to fetch intraday capital flow data (minute-level) for a given stock code and processes the result using process_data before returning it as a dict.
    @mcp.tool()
    def capital_flow(stock_code: str="SZ000002") -> dict:
        """获取当日资金流如流出数据,每分钟数据"""
        result = ball.capital_flow(stock_code)
        return process_data(result)
  • main.py:34-61 (helper)
    Shared helper function used by the capital_flow tool (and others) to process the raw data, primarily converting timestamps to readable datetime strings.
    def process_data(data, process_config=None):
        """
        通用数据处理函数,可扩展添加各种数据处理操作
        
        Args:
            data: 原始数据
            process_config: 处理配置字典,用于指定要执行的处理操作
                例如: {'convert_timestamps': True, 'other_process': params}
        
        Returns:
            处理后的数据
        """
        if process_config is None:
            # 默认配置
            process_config = {
                'convert_timestamps': True
            }
        
        # 如果开启了时间戳转换
        if process_config.get('convert_timestamps', True):
            data = convert_timestamps(data)
        
        # 在这里可以添加更多的数据处理逻辑
        # 例如:
        # if 'format_numbers' in process_config:
        #     data = format_numbers(data, **process_config['format_numbers'])
        
        return data
  • main.py:14-31 (helper)
    Helper function called by process_data to recursively convert timestamp fields in the data to formatted datetime strings.
    def convert_timestamps(data):
        """递归地将数据中的所有 timestamp 转换为 datetime 字符串"""
        if isinstance(data, dict):
            for key, value in list(data.items()):
                if key == 'timestamp' and isinstance(value, (int, float)) and value > 1000000000000:  # 毫秒级时间戳
                    data[key] = datetime.datetime.fromtimestamp(value/1000).strftime('%Y-%m-%d %H:%M:%S')
                elif key == 'timestamp' and isinstance(value, (int, float)) and value > 1000000000:  # 秒级时间戳
                    data[key] = datetime.datetime.fromtimestamp(value).strftime('%Y-%m-%d %H:%M:%S')
                elif key.endswith('_date') and isinstance(value, (int, float)) and value > 1000000000000:  # 毫秒级时间戳
                    data[key] = datetime.datetime.fromtimestamp(value/1000).strftime('%Y-%m-%d %H:%M:%S')
                elif key.endswith('_date') and isinstance(value, (int, float)) and value > 1000000000:  # 秒级时间戳
                    data[key] = datetime.datetime.fromtimestamp(value).strftime('%Y-%m-%d %H:%M:%S')
                elif isinstance(value, (dict, list)):
                    data[key] = convert_timestamps(value)
        elif isinstance(data, list):
            for i, item in enumerate(data):
                data[i] = convert_timestamps(item)
        return data
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions data retrieval ('获取') but lacks details on permissions, rate limits, data freshness, or response format. For a tool that likely involves real-time or sensitive financial data, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with a single sentence in Chinese, front-loading the core purpose. It efficiently states the action and data type without unnecessary elaboration, though it could be slightly clearer in English translation for broader accessibility.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of financial data tools, no annotations, no output schema, and low schema coverage, the description is incomplete. It doesn't address key aspects like data format, update frequency, error handling, or how it differs from siblings, leaving the agent with insufficient context for reliable use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds no parameter information beyond what the schema provides. With 0% schema description coverage and one parameter ('stock_code'), the description doesn't compensate by explaining the parameter's role, format, or default value implications. However, since there's only one parameter, the baseline is adjusted to 3, as the agent can infer it's for specifying a stock.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool '获取当日资金流如流出数据,每分钟数据' (gets daily capital flow and outflow data, minute-by-minute data), which provides a clear verb ('获取') and resource ('资金流数据'). However, it doesn't differentiate from sibling tools like 'capital_history' or 'capital_assort', leaving ambiguity about scope or granularity distinctions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives is provided. The description implies it's for current-day, minute-level capital flow data, but it doesn't specify prerequisites, exclusions, or compare to siblings like 'capital_history' for historical data or 'cash_flow' for broader financial metrics.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/liqiongyu/xueqiu_mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server