Skip to main content
Glama
narumiruna

Yahoo Finance MCP Server

yfinance_get_financials

Read-onlyIdempotent

Retrieve income statements, balance sheets, and cash flow data for any stock ticker. Analyze financial trends and calculate ratios across annual, quarterly, or trailing twelve months periods.

Instructions

Fetch financial statements (income statement, balance sheet, and cash flow) with historical data.

Returns JSON with income statement, balance sheet, and cash flow data across reporting periods.

Use the data to analyze trends, calculate ratios, or compare periods.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
symbolYesStock ticker symbol (e.g., 'AAPL', 'GOOGL', 'MSFT')
frequencyNoReporting frequency: 'annual' for yearly, 'quarterly' for quarterly, or 'ttm' for trailing twelve monthsannual

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • Tool registration via @mcp.tool() decorator with name 'yfinance_get_financials', readonly, idempotent hint.
    @mcp.tool(
        name="yfinance_get_financials",
        annotations=ToolAnnotations(
            readOnlyHint=True,
            destructiveHint=False,
            idempotentHint=True,
            openWorldHint=True,
        ),
    )
  • Async handler 'get_financials' that fetches income statement, balance sheet, and cash flow for a given symbol/frequency.
    async def get_financials(
        symbol: Annotated[str, Field(description="Stock ticker symbol (e.g., 'AAPL', 'GOOGL', 'MSFT')")],
        frequency: Annotated[
            str,
            Field(
                description=(
                    "Reporting frequency: 'annual' for yearly, 'quarterly' for quarterly, "
                    "or 'ttm' for trailing twelve months"
                )
            ),
        ] = "annual",
    ) -> str:
        """Fetch financial statements (income statement, balance sheet, and cash flow) with historical data.
    
        Returns JSON with income statement, balance sheet, and cash flow data across reporting periods.
    
        Use the data to analyze trends, calculate ratios, or compare periods.
        """
        try:
            ticker = await asyncio.to_thread(yf.Ticker, symbol)
        except _RETRYABLE_YFINANCE_EXCEPTIONS as exc:
            return _create_retryable_error_response(f"fetching financials for '{symbol}'", exc, {"symbol": symbol})
        except Exception as exc:
            return create_error_response(
                f"Failed to fetch financials for '{symbol}'. Verify the symbol is correct.",
                error_code="API_ERROR",
                details={"symbol": symbol, "exception": str(exc)},
            )
    
        income_stmt = None
        balance_sheet = None
        cash_flow = None
    
        if frequency not in {"annual", "quarterly", "ttm"}:
            return create_error_response(
                f"Invalid frequency '{frequency}'. Valid options: 'annual', 'quarterly', 'ttm'.",
                error_code="INVALID_PARAMS",
                details={"frequency": frequency, "valid_options": ["annual", "quarterly", "ttm"]},
            )
    
        try:
            if frequency == "annual":
                income_stmt = await asyncio.to_thread(lambda: ticker.income_stmt)
                balance_sheet = await asyncio.to_thread(lambda: ticker.balance_sheet)
                cash_flow = await asyncio.to_thread(lambda: ticker.cashflow)
            elif frequency == "quarterly":
                income_stmt = await asyncio.to_thread(lambda: ticker.quarterly_income_stmt)
                balance_sheet = await asyncio.to_thread(lambda: ticker.quarterly_balance_sheet)
                cash_flow = await asyncio.to_thread(lambda: ticker.quarterly_cashflow)
            else:
                income_stmt = await asyncio.to_thread(lambda: ticker.ttm_income_stmt)
                balance_sheet = None  # TTM balance sheet not directly available
                cash_flow = None  # TTM cash flow not directly available
    
            result = _build_financials_response(income_stmt, balance_sheet, cash_flow)
        except _RETRYABLE_YFINANCE_EXCEPTIONS as exc:
            return _create_retryable_error_response(
                f"fetching financials for '{symbol}'",
                exc,
                {"symbol": symbol, "frequency": frequency},
            )
        except Exception as exc:
            return create_error_response(
                f"Failed to fetch financials for '{symbol}'. Verify the symbol is correct.",
                error_code="API_ERROR",
                details={"symbol": symbol, "frequency": frequency, "exception": str(exc)},
            )
        if not result:
            return create_error_response(
                f"No financial data available for '{symbol}' with frequency='{frequency}'.",
                error_code="NO_DATA",
                details={"symbol": symbol, "frequency": frequency},
            )
    
        return dump_json(result)
  • Helper '_build_financials_response' transforms DataFrames into a dict with income_statement, balance_sheet, and cash_flow fields.
    def _build_financials_response(income_stmt, balance_sheet, cash_flow=None) -> dict:
        """Build financials response from income statement, balance sheet, and cash flow DataFrames."""
        result = {}
    
        if income_stmt is not None and not income_stmt.empty:
            income_fields = [
                "EBIT",
                "Net Income",
                "Tax Provision",
                "Pretax Income",
                "Interest Expense",
                "Total Revenue",
                "Operating Income",
                "EBITDA",
                "Normalized Income",
            ]
            available_income_fields = [f for f in income_fields if f in income_stmt.index]
            result["income_statement"] = {}
            for field in available_income_fields:
                result["income_statement"][field] = {
                    str(col.date()): income_stmt.loc[field, col] for col in income_stmt.columns
                }
    
        if balance_sheet is not None and not balance_sheet.empty:
            balance_fields = [
                "Stockholders Equity",
                "Total Debt",
                "Cash And Cash Equivalents",
                "Invested Capital",
                "Net Debt",
                "Total Assets",
                "Total Liabilities Net Minority Interest",
                "Net Tangible Assets",
                "Tangible Book Value",
            ]
            available_balance_fields = [f for f in balance_fields if f in balance_sheet.index]
            result["balance_sheet"] = {}
            for field in available_balance_fields:
                result["balance_sheet"][field] = {
                    str(col.date()): balance_sheet.loc[field, col] for col in balance_sheet.columns
                }
    
        if cash_flow is not None and not cash_flow.empty:
            cash_flow_fields = [
                "Operating Cash Flow",
                "Free Cash Flow",
                "Capital Expenditure",
                "Net Income From Continuing Operations",
                "Depreciation And Amortization",
                "Change In Working Capital",
                "Cash Dividends Paid",
            ]
            available_cash_flow_fields = [f for f in cash_flow_fields if f in cash_flow.index]
            result["cash_flow"] = {}
            for field in available_cash_flow_fields:
                result["cash_flow"][field] = {str(col.date()): cash_flow.loc[field, col] for col in cash_flow.columns}
    
        return result
  • Helper '_create_retryable_error_response' creates standardized retryable/rate-limit error responses.
    def _create_retryable_error_response(action: str, exc: BaseException, details: dict[str, Any]) -> str:
        if _is_rate_limit_error(exc):
            message = f"Rate limit reached while {action}. Try again later."
        else:
            message = f"Temporary network issue while {action}. Try again later."
    
        return create_error_response(message, error_code="NETWORK_ERROR", details={**details, "exception": str(exc)})
  • Helper 'create_error_response' and 'dump_json' used for error formatting and JSON serialization.
    def create_error_response(message: str, error_code: ErrorCode = "UNKNOWN_ERROR", details: dict | None = None) -> str:
        """Create a structured error response.
    
        Args:
            message: Human-readable error message
            error_code: Machine-readable error code for client handling
            details: Optional additional error details
    
        Returns:
            JSON string with error information
        """
        error_obj: dict[str, object] = {"error": message, "error_code": error_code}
        if details:
            error_obj["details"] = details
        return dump_json(error_obj)
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true, so the safety profile is clear. Description adds that it returns historical data and the structure of the output (income, balance sheet, cash flow), which is useful but not extensive behavioral context. No contradictions with annotations.

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

Conciseness5/5

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

Three sentences, each serving a purpose: first defines the action, second describes output, third suggests usage. No unnecessary words or redundancy. Appropriately sized and front-loaded.

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

Completeness4/5

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

Given the presence of an output schema (so return format is documented elsewhere), the description covers the tool's purpose, output structure, and typical use cases. It is adequate for a simple read-only tool, though it could mention data range or limitations.

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?

Input schema has 100% coverage with descriptions for both parameters (symbol and frequency). Description does not add any new semantics beyond the schema; it only mentions 'historical data' which is implied by the tool's nature. Baseline 3 is appropriate.

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

Purpose5/5

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

Description clearly states it fetches financial statements (income, balance sheet, cash flow) with historical data. Verb 'Fetch' and resource 'financial statements' are specific, and the tool is well-distinguished from siblings like price history or holders.

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

Usage Guidelines3/5

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

Description says 'Use the data to analyze trends, calculate ratios, or compare periods' which implies usage context but does not explicitly state when to use vs alternatives or when not to use. No exclusions or comparisons to siblings provided.

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/narumiruna/yfinance-mcp'

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