Skip to main content
Glama

get_history_market_data

Retrieve historical market data for specified stock codes, date ranges, and periods with customizable fields using the XTQuantAI MCP server.

Instructions

获取历史行情数据

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
codesYes股票代码列表,用逗号分隔,例如 "000001.SZ,600519.SH"
end_dateNo结束日期,格式为 "YYYYMMDD",为空表示当前日期
fieldsNo字段列表,用逗号分隔,为空表示所有字段
periodNo周期,例如 "1d", "1m", "5m" 等1d
start_dateNo开始日期,格式为 "YYYYMMDD"

Implementation Reference

  • The core handler function that implements the tool logic. It parses input, calls xtdata.get_market_data to fetch historical market data for given stock codes, period, dates, and fields, converts numpy arrays to lists, and returns the data as a dictionary.
    async def get_history_market_data(input: GetMarketDataInput) -> Dict[str, Any]:
        """
        获取历史行情数据
        
        Args:
            codes: 股票代码列表,用逗号分隔,例如 "000001.SZ,600519.SH"
            period: 周期,例如 "1d", "1m", "5m" 等
            start_date: 开始日期,格式为 "YYYYMMDD"
            end_date: 结束日期,格式为 "YYYYMMDD",为空表示当前日期
            fields: 字段列表,用逗号分隔,为空表示所有字段
            
        Returns:
            历史行情数据
        """
        try:
            # 确保XTQuant数据中心已初始化
            ensure_xtdc_initialized()
            
            if xtdata is None:
                return {"error": "xtdata模块未正确加载"}
            
            # 解析股票代码列表
            codes = [code.strip() for code in input.codes.split(",") if code.strip()]
            if not codes:
                return {"error": "未提供有效的股票代码"}
            
            # 解析字段列表
            fields = []
            if input.fields:
                fields = [field.strip() for field in input.fields.split(",") if field.strip()]
            
            # 如果未指定字段,使用默认字段
            if not fields:
                fields = ["open", "high", "low", "close", "volume"]
            
            print(f"获取历史行情数据: 股票={codes}, 周期={input.period}, 字段={fields}, 开始日期={input.start_date}, 结束日期={input.end_date}")
            
            try:
                # 获取历史行情数据
                print(f"调用xtdata.get_market_data({fields}, {codes}, {input.period}, {input.start_date}, {input.end_date})")
                data = xtdata.get_market_data(fields, codes, period=input.period, 
                                              start_time=input.start_date, end_time=input.end_date)
                
                # 处理返回值
                if data is None:
                    return {"error": "获取历史行情数据失败"}
                
                # 将数据转换为可序列化的格式
                result = {}
                for code, stock_data in data.items():
                    code_result = {}
                    for field, values in stock_data.items():
                        # 将numpy数组转换为列表
                        if hasattr(values, "tolist"):
                            code_result[field] = values.tolist()
                        else:
                            code_result[field] = list(values)
                    result[code] = code_result
                
                return result
            except Exception as e:
                print(f"获取历史行情数据出错: {str(e)}")
                traceback.print_exc()
                return {"error": f"获取历史行情数据失败: {str(e)}"}
        except Exception as e:
            print(f"处理历史行情数据请求出错: {str(e)}")
            traceback.print_exc()
            return {"error": str(e)}
  • Pydantic model defining the input schema for the get_history_market_data tool, matching the inputSchema in registration.
    class GetMarketDataInput(BaseModel):
        codes: str  # 股票代码列表,用逗号分隔,例如 "000001.SZ,600519.SH"
        period: str = "1d"  # 周期,例如 "1d", "1m", "5m" 等
        start_date: str = ""  # 开始日期,格式为 "YYYYMMDD"
        end_date: str = ""  # 结束日期,格式为 "YYYYMMDD",为空表示当前日期
        fields: str = ""  # 字段列表,用逗号分隔,为空表示所有字段
  • MCP tool registration in handle_list_tools(), defining name, description, and input schema for the tool.
    types.Tool(
        name="get_history_market_data",
        description="获取历史行情数据",
        inputSchema={
            "type": "object",
            "properties": {
                "codes": {
                    "type": "string",
                    "description": "股票代码列表,用逗号分隔,例如 \"000001.SZ,600519.SH\""
                },
                "period": {
                    "type": "string",
                    "description": "周期,例如 \"1d\", \"1m\", \"5m\" 等",
                    "default": "1d"
                },
                "start_date": {
                    "type": "string",
                    "description": "开始日期,格式为 \"YYYYMMDD\"",
                    "default": ""
                },
                "end_date": {
                    "type": "string",
                    "description": "结束日期,格式为 \"YYYYMMDD\",为空表示当前日期",
                    "default": ""
                },
                "fields": {
                    "type": "string",
                    "description": "字段列表,用逗号分隔,为空表示所有字段",
                    "default": ""
                }
            },
            "required": ["codes"]
        }
    ),
  • Tool dispatch logic in the MCP server's @server.call_tool() handler, which validates arguments, creates input model, calls the handler function, and formats response.
    elif name == "get_history_market_data":
        if not arguments or "codes" not in arguments:
            return [types.TextContent(type="text", text="错误: 缺少必要参数 'codes'")]
        
        # 处理字符串格式的codes参数
        codes_str = arguments["codes"]
        codes = [code.strip() for code in codes_str.split(",") if code.strip()]
        
        period = arguments.get("period", "1d")
        start_date = arguments.get("start_date", "")
        end_date = arguments.get("end_date", "")
        
        # 处理字符串格式的fields参数
        fields_str = arguments.get("fields", "")
        fields = [field.strip() for field in fields_str.split(",") if field.strip()]
        
        input_model = GetMarketDataInput(codes=codes_str, period=period, start_date=start_date, end_date=end_date, fields=fields_str)
        result = await get_history_market_data(input_model)
        return [types.TextContent(type="text", text=json.dumps(result, ensure_ascii=False, indent=2))]
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 states the action ('获取' - get) but doesn't reveal any behavioral traits like whether this is a read-only operation, potential rate limits, authentication needs, or what the output format might be. This is a significant gap for a tool with 5 parameters and no output schema.

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 a single phrase ('获取历史行情数据'), which is highly concise and front-loaded with the core purpose. There is no wasted text, making it efficient, though it could benefit from slightly more detail to enhance clarity without sacrificing brevity.

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 a 5-parameter tool with no annotations and no output schema, the description is incomplete. It doesn't address key contextual aspects like the return format, error handling, or how it integrates with sibling tools. This leaves gaps that could hinder an AI agent's ability to use the tool effectively.

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 schema description coverage is 100%, with all parameters well-documented in the input schema (e.g., 'codes' as stock codes, 'period' as time intervals). The description adds no additional meaning beyond what the schema provides, such as explaining parameter interactions or default behaviors. Given the high schema coverage, a baseline score of 3 is appropriate.

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 '获取历史行情数据' (Get historical market data) states a clear verb ('获取' - get) and resource ('历史行情数据' - historical market data), establishing the basic purpose. However, it lacks specificity about what type of market data (e.g., stocks, indices) and doesn't differentiate from sibling tools like 'get_full_market_data' or 'get_latest_market_data', making it somewhat vague.

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?

The description provides no guidance on when to use this tool versus alternatives. There are no explicit instructions, implied contexts, or exclusions mentioned, such as how it differs from 'get_latest_market_data' for real-time data or 'get_full_market_data' for broader data. This leaves the agent without usage direction.

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

Related 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/dfkai/xtquantai'

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