yfinance-ai: Yahoo Finance MCP server

yfinance-ai MCP server

<!-- mcp-name: io.github.lkcair/yfinance-ai -->

World's first AI-powered Yahoo Finance integration: 68 tools for stocks, ETFs, mutual funds, crypto, forex and commodities, in one Python file.

🚀 Thousands of downloads on ClawHub and OpenWebUI

Prices and history, financial statements, ratios and valuation history, analyst estimates and price targets, earnings, dividends, options, holders and insiders, funds and ETFs, market movers, sectors and industries, and earnings, IPO, economic and split calendars.

Install

Needs uv. No API key.

Claude Code:

claude mcp add yfinance-ai -- uvx yfinance-ai@latest

VS Code:

code --add-mcp '{"name":"yfinance-ai","type":"stdio","command":"uvx","args":["yfinance-ai@latest"]}'

Claude Desktop, Cursor, Windsurf and other clients, in the client's MCP config file:

{
  "mcpServers": {
    "yfinance-ai": {
      "command": "uvx",
      "args": [
        "yfinance-ai@latest"
      ]
    }
  }
}

@latest picks up new releases when the client starts. Without uv: pip install yfinance-ai, then use "command": "yfinance-ai" with no args.

Listed in the MCP Registry as io.github.lkcair/yfinance-ai. Every tool is read-only.

Agent frameworks

The server runs over stdio with uvx yfinance-ai@latest, so any framework with MCP support can load all its tools.

LangChain: pip install "langchain[mcp]" langchain-anthropic

import asyncio
from langchain.agents import create_agent
from langchain.mcp import MCPAdapter

async def main():
    config = {"mcpServers": {"yfinance-ai": {
        "command": "uvx", "args": ["yfinance-ai@latest"],
    }}}
    async with MCPAdapter(config) as adapter:
        tools = await adapter.list_tools()
        agent = create_agent("claude-sonnet-5", tools)
        result = await agent.ainvoke({"messages": [{"role": "user", "content": "What is Apple's P/E, and how does it compare with Microsoft and Google?"}]})
        print(result["messages"][-1].content)

asyncio.run(main())

Google ADK: pip install "google-adk[mcp]"

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import StdioConnectionParams
from mcp import StdioServerParameters

root_agent = LlmAgent(
    model="gemini-flash-latest",
    name="yfinance_ai",
    instruction="Answer with the yfinance-ai tools.",
    tools=[McpToolset(connection_params=StdioConnectionParams(
        server_params=StdioServerParameters(command="uvx", args=["yfinance-ai@latest"]),
        timeout=60,
    ))],
)

Shortened. The full README is on GitHub.