A collection of MCP server implementations demonstrating various use cases including stock analysis, stock price tracking, SQLite database queries, and basic calculator operations
Server has 8 tools with basic descriptions and schemas, but significant quality gaps. Descriptions are present but generic (avg ~80 chars, below 194-char baseline). No error handling guidance, no output schema documentation, no tool annotations. Tool naming is reasonable (verb_noun pattern) but parameter documentation is severely deficient. Stock analysis tools expose API keys in code (security issue). No pagination support despite tools returning lists. Schemas are present but incomplete, many parameters lack descriptions entirely.
Add two numbers and return the result.
Calculate short and long moving averages for a symbol
Calculate Relative Strength Index (RSI) for a symbol
Compare the current stock prices of two ticker symbols. Returns a formatted message comparing the two stock prices.
Retrieve historical data for a stock given a ticker symbol and a period. Returns the historical data as a CSV formatted string.
Retrieve the current stock price for the given ticker symbol. Returns the latest closing price as a float.
API key exposed in source code (stock_analysis_server.py line: API_KEY = '6BZ33KPJPJ09AQAP'). Credentials must use server-side secret injection via environment variables.
get_top_chatters has empty input schema ({}) but no documentation of what it returns or how to paginate results. No output schema documented.
No error handling guidance in any tool. Descriptions do not explain what to do if API calls fail, rate limits are hit, or invalid symbols are provided. Missing recovery patterns.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 48 | 2026-07-28+ | v2 |
Retrieve the top chatters sorted by number of messages.
Provide a comprehensive trade recommendation based on multiple indicators
Tools returning lists (get_top_chatters, get_stock_history) lack pagination parameters (limit, offset, page_size). No total count or next_cursor returned. Large result sets will blow context window.
Parameter descriptions are missing or minimal. 'symbol' appears in 6 tools but only 2 have descriptions. 'period' in get_stock_history lacks format guidance (what does '1mo' mean exactly?). LLMs cannot infer parameter semantics from names alone.