通达信金融数据服务 MCP 插件,提供 A 股行情、K线、F10 基本面、智能选股等 6 个核心工具,内置 45 个投资分析技能
Server has 6 tools with basic schemas and descriptions, but significant quality gaps. Tool names lack clear action verbs (tdx_api_data, tdx_quotes, tdx_kline, tdx_screener, tdx_f10, tdx_board_analysis are domain-specific but not verb-prefixed). Descriptions exist but are brief (avg ~80 chars) and lack actionable context for LLM selection. Parameter descriptions are minimal; many lack type clarity. No documented output schemas visible. Error handling and recovery guidance absent. Security: API token handling via environment variables is correct, but no per-tool permission gates or audit logging evident.
通达信 API 数据查询工具,支持多种金融数据接口(涨停、K线、基本面等)
板块分析工具,获取板块行情、成份股、涨幅排名等数据
获取股票 F10 基本面数据,包括公司简介、财务指标、主营业务等
获取股票 K 线数据,支持多个周期(日线、周线、月线等)
获取股票实时行情数据,包括价格、成交量、委比等信息
智能选股工具,支持涨停、跌停、热门题材等多种筛选条件
Tool names lack action verbs. Names like 'tdx_api_data', 'tdx_quotes', 'tdx_kline' are domain-specific but do not start with clear verbs (get_, list_, search_). LLMs cannot infer intent from names alone.
Output schemas not documented. No visible schema definitions for tool responses. LLMs cannot plan downstream calls or extract required fields without knowing response structure.
Parameter descriptions are minimal and lack actionable constraints. E.g., 'setcode' described as 'market code, 0=深圳, 1=上海' but no enum constraint visible. 'wantNum' lacks type clarity (string vs integer mismatch).
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 45 | 2026-07-28+ | v2 |
No error handling or recovery guidance. Tools lack descriptions of failure modes, retryability, or actionable error messages. Agents cannot self-correct on failures.
Tool descriptions are generic and lack WHEN/WHY context. E.g., 'get stock real-time quote data' does not explain when to use tdx_quotes vs tdx_api_data, or what fields are returned.