Best for
- Developers and investors who need quick access to Yahoo Finance data
- Users performing financial analysis, market research, and investment research with Claude
- Users who want to integrate financial data into MCP client workflows
Y
Yahoo Finance MCP Server
Community
Comprehensive Yahoo Finance data via the Model Context Protocol.
- Category
- Other #168 of 230
- Stars
- ★ 361 Popular
- Transport
- stdio (local process)
- Runtime
- Python 3.11+
- Credentials
- No credential needed
- License
- MIT
- Last commit
- Tools
- 9
47FMRS · D
This MCP server offers a rich set of Yahoo Finance data tools covering stock information, financial statements, options, and analyst recommendations. Installation is straightforward via uvx. Suitable for developers and investors needing quick financial data. However, it relies on third-party data sources which may be unstable, and data accuracy should be verified.
Strongest · Setup experience 13/20 Weakest · Reliability 5/20
Why each score
- Reliability 5/20
- The supplied evidence is limited to the README and repository metadata; no server.py, pyproject.toml, or tests were available, so the MCP init/tool-list handshake and the advertised tool schemas cannot be verified. The nine listed tools are plausible but unsupported by reproducible execution evidence, and there is no CI or committed test suite to anchor a higher score.
- Security and permissions 8/20
- The README describes a read-only financial data service with no credentials, secrets, or destructive operations; the obvious boundary is outbound requests to Yahoo Finance. Deductions are made because no source-level audit was possible, no permission/network scoping is declared, and the handling of user-supplied tickers and yfinance output is unverified.
- Maintenance 9/20
- The repository is not archived and has an explicit MIT license, which provides some baseline. However, release history, commit activity, issue responsiveness, dependency updates, and a security-response channel are all absent from the supplied evidence, so the repository cannot be shown as actively sustained.
- Documentation 12/20
- The README is usable: it lists tools, gives realistic use cases, states Python 3.11+, provides uvx/local setup, and includes Claude Desktop configuration examples. It is docked for lacking per-tool parameter details, rate/usage limitations, troubleshooting guidance, cost notes, and dependency depth, and for not showing whether the Chinese README has equivalent completeness.
- Setup experience 13/20
- Setup is straightforward on paper: run via uvx from the Git URL, or install locally with uv, and copy the provided Claude Desktop config examples for macOS/Windows. The score is capped below 15 because no verifiable CI or committed install/run tests were supplied, and the remote-Git invocation may be fragile across Python/platform versions.
Static review · not runListed 2026-08-07
Read the FMRS scoring method →Fit and risk
What it can accessUses the network
Not for
- Scenarios requiring real-time or ultra-low latency data (data comes from Yahoo Finance and may be delayed)
- Scenarios requiring official, authoritative, or verified financial data (data comes from Yahoo Finance and may be incomplete or inaccurate)
- Long-running stable servers, as it depends on third-party Yahoo Finance API which may be unstable
Required permissions
- No API key or additional permissions required; directly accesses Yahoo Finance public data.
- Communicates with MCP clients via standard I/O.
- Requires network access to Yahoo Finance to fetch data.
Risks and side effects
- Dependency on third-party Yahoo Finance service; data may be unavailable due to outages or API changes.
- Data may be delayed or inaccurate; use with caution for investment decisions.
- Rate limits may apply; high-frequency calls could lead to request rejection.
Setup
Before you start
Runtime：Python 3.11+
- Ensure Python 3.11 or higher is installed.
- Run directly with uvx:
uvx --from git+https://github.com/Alex2Yang97/yahoo-finance-mcp yahoo-finance-mcp. - Or clone the repository and install locally:
git clone https://github.com/Alex2Yang97/yahoo-finance-mcp.git, enter the directory, create a virtual environment, and install dependencies. - For Claude Desktop, edit the config file to add the MCP server configuration above, then restart Claude Desktop.
claude_desktop_config.json
{
"mcpServers": {
"yfinance": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/Alex2Yang97/yahoo-finance-mcp",
"yahoo-finance-mcp"
]
}
}
}
Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
.vscode/mcp.json
{
"servers": {
"yfinance": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/Alex2Yang97/yahoo-finance-mcp",
"yahoo-finance-mcp"
]
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
Terminal
claude mcp add yfinance -- uvx --from git+https://github.com/Alex2Yang97/yahoo-finance-mcp yahoo-finance-mcp
Run it in a terminal; replace any <…> placeholders with your own values first.
Check that it works
Add the yfinance server to claude_desktop_config. and restart Claude for Desktop; tools like get_stock_info should appear in the tool list, and asking for AAPL's current stock data should return live results.
Troubleshooting
- Ensure network connectivity to Yahoo Finance is working.
- Ensure Python version meets the requirement (3.11+).
- Verify dependencies are correctly installed, especially yfinance and mcp.
- For Claude Desktop, ensure the uvx command is in PATH or use the full path.
- If tools produce no output, try restarting the MCP server.
Things to try
Once connected, you can ask your AI assistant things like:
- Show me the historical stock prices for AAPL over the last 6 months with daily intervals.
- Get the quarterly balance sheet for Microsoft.
- Get the options chain for SPY with expiration date 2024-06-21 for calls.
- What are the analyst recommendations for Amazon?
Tools 9
get_historical_stock_prices read-only
Get historical OHLCV data for a stock with customizable period and interval.
get_stock_info read-only
Get comprehensive stock data including price, metrics, and company details.
get_yahoo_finance_news read-only
Get latest news articles for a stock.
get_stock_actions read-only
Get stock dividends and splits history.
get_financial_statement read-only
Get income statement, balance sheet, or cash flow statement (annual/quarterly).
get_holder_info read-only
Get major holders, institutional holders, mutual funds, or insider transactions.
get_option_expiration_dates read-only
Get available options expiration dates.
get_option_chain read-only
Get options chain for a specific expiration date and type (calls/puts).
Show 1 more tools
get_recommendations read-only
Get analyst recommendations or upgrades/downgrades history.
No matching tools
Use cases
Show me the historical stock prices for AAPL over the last 6 months with daily intervals.
Get the quarterly balance sheet for Microsoft.
What are the key financial metrics for Tesla from the stock info?
Compare the quarterly income statements of Amazon and Google.
Show me the annual cash flow statement for NVIDIA.
Get the latest news articles about Meta Platforms.
Show me the institutional holders of Apple stock.
What are the recent insider transactions for Tesla?
Get the options chain for SPY with expiration date 2024-06-21 for calls.
What are the analyst recommendations for Amazon over the last 3 months?
Supported clients
Claude Desktop
Listed from the project's documentation, not tested by this site.
Overview
This is a Model Context Protocol (MCP) server that provides comprehensive financial data from Yahoo Finance. It allows you to retrieve detailed information about stocks, including historical prices, company information, financial statements, options data, and market news.
Similar servers
Hevy MCP
77 · B
Manage your Hevy workout data from AI assistants via MCP.
Firecrawl MCP Server
75 · B
Firecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
BioMCP
75 · B
One binary. One grammar. Evidence from the biomedical sources you already trust.
Compartment
75 · B
Encrypted, fully offline long-term memory for AI agents
Source revision b9c176547d37 Data synced 2026-10-12 Read the FMRS scoring method