Skip to main content
Glama
marckwei

MCP Yahoo Finance

by marckwei

get_recommendations

Retrieve analyst recommendations for stocks to inform investment decisions using Yahoo Finance data.

Instructions

Get analyst recommendations for a given symbol.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
symbolYesStock symbol in Yahoo Finance format.

Implementation Reference

  • The primary handler function implementing the tool logic: fetches analyst recommendations using yfinance's Ticker.get_recommendations(), formats as JSON if DataFrame.
    def get_recommendations(self, symbol: str) -> str:
        """Get analyst recommendations for a given symbol.
    
        Args:
            symbol (str): Stock symbol in Yahoo Finance format.
        """
        stock = Ticker(ticker=symbol, session=self.session)
        recommendations = stock.get_recommendations()
        print(recommendations)
        if isinstance(recommendations, pd.DataFrame):
            return f"{recommendations.to_json(orient='records', indent=2)}"
        return f"{recommendations}"
  • Tool registration in the MCP server's list_tools() method, where generate_tool(yf.get_recommendations) creates and returns the Tool instance with schema.
    @server.list_tools()
    async def list_tools() -> list[Tool]:
        return [            
            generate_tool(yf.cmd_run),
            generate_tool(yf.get_recommendations),
            generate_tool(yf.get_news),
            generate_tool(yf.get_current_stock_price),
            generate_tool(yf.get_stock_price_by_date),
            generate_tool(yf.get_stock_price_date_range),
            generate_tool(yf.get_historical_stock_prices),
            generate_tool(yf.get_dividends),
            generate_tool(yf.get_income_statement),
            generate_tool(yf.get_cashflow),
            generate_tool(yf.get_earning_dates),
        ]
  • MCP server call_tool dispatcher case that invokes the get_recommendations handler and returns the result as TextContent.
    case "get_recommendations":
        recommendations = yf.get_recommendations(**args)
        return [TextContent(type="text", text=recommendations)]
  • Dynamic schema generation for all tools, including get_recommendations, based on function signature, type annotations, and Google-style docstring.
    def generate_tool(func: Any) -> Tool:
        """Generates a tool schema from a Python function."""
        signature = inspect.signature(func)
        docstring = inspect.getdoc(func) or ""
        param_descriptions = parse_docstring(docstring)
    
        schema = {
            "name": func.__name__,
            "description": docstring.split("Args:")[0].strip(),
            "inputSchema": {
                "type": "object",
                "properties": {},
            },
        }
    
        for param_name, param in signature.parameters.items():
            param_type = (
                "number"
                if param.annotation is float
                else "string"
                if param.annotation is str
                else "string"
            )
            schema["inputSchema"]["properties"][param_name] = {
                "type": param_type,
                "description": param_descriptions.get(param_name, ""),
            }
    
            if "required" not in schema["inputSchema"]:
                schema["inputSchema"]["required"] = [param_name]
            else:
                if "=" not in str(param):
                    schema["inputSchema"]["required"].append(param_name)
    
        return Tool(**schema)
  • Helper function used by generate_tool to parse docstrings for parameter descriptions in the tool schema.
    def parse_docstring(docstring: str) -> dict[str, str]:
        """Parses a Google-style docstring to extract parameter descriptions."""
        descriptions = {}
        if not docstring:
            return descriptions
    
        lines = docstring.split("\n")
        current_param = None
    
        for line in lines:
            line = line.strip()
            if line.startswith("Args:"):
                continue
            elif line and "(" in line and ")" in line and ":" in line:
                param = line.split("(")[0].strip()
                desc = line.split("):")[1].strip()
                descriptions[param] = desc
                current_param = param
            elif current_param and line:
                descriptions[current_param] += " " + line.strip()
    
        return descriptions

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

C2.9/5.0
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 ('Get') but doesn't describe any traits like whether it's a read-only operation, potential rate limits, data freshness, or what the output format looks like (e.g., list of recommendations, summary). This is a significant gap for a tool with no annotation coverage.

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?

The description is a single, efficient sentence that directly states the tool's purpose without any unnecessary words. It is appropriately sized and front-loaded, making it easy to parse quickly.

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, and no output schema, the description is incomplete. It doesn't explain what 'analyst recommendations' entail (e.g., buy/sell ratings, target prices), how results are returned, or any behavioral aspects, leaving the agent with insufficient context for effective 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 schema description coverage is 100%, with the single parameter 'symbol' fully documented in the schema as 'Stock symbol in Yahoo Finance format.' The description adds no additional meaning beyond this, so it meets the baseline for high schema coverage without compensating value.

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

Purpose4/5

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

The description clearly states the tool's purpose with a specific verb ('Get') and resource ('analyst recommendations'), specifying it's for a given symbol. However, it doesn't differentiate from sibling tools like get_news or get_current_stock_price, which might also provide related financial data, so it doesn't reach the highest clarity level.

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. It doesn't mention any context, prerequisites, or exclusions, leaving the agent to infer usage from the tool name alone among many financial data siblings.

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