MCP-Server-Financial-Analyzer
Provides AI assistants with real-time stock prices, financial statements, SEC filings, and analytical tools like DCF valuation and ratio analysis.
README
MCP Server – Financial Analyzer
An MCP (Model Context Protocol) server that gives AI assistants access to real-time stock prices, financial statements, SEC filings, and analytical tools.
Built with FastMCP, powered by yfinance and edgartools.
Tools
Stock Prices
| Tool | Description |
|---|---|
get_stock_price |
Current price, volume, 52-week range, market cap |
get_price_history |
OHLCV history with configurable period and interval |
get_stock_info |
Company profile, sector, employees, ownership |
Fundamentals
| Tool | Description |
|---|---|
get_income_statement |
Revenue, gross profit, EBITDA, net income, EPS |
get_balance_sheet |
Assets, liabilities, equity, debt |
get_cash_flow |
Operating, investing, financing, free cash flow |
get_earnings_history |
EPS estimates vs actuals and surprise % |
SEC Filings
| Tool | Description |
|---|---|
search_sec_filings |
List 10-K, 10-Q, 8-K, and other filings |
get_filing_sections |
Retrieve full text of specific sections (business, risk_factors, mda) |
get_company_facts |
EDGAR CIK, registered tickers, TTM financials from XBRL |
Analysis
| Tool | Description |
|---|---|
calculate_financial_ratios |
P/E, P/B, EV/EBITDA, ROE, ROA, margins, leverage ratios |
analyze_trends |
YoY growth trends for any financial line item |
compare_stocks |
Side-by-side comparison of multiple tickers on any metric |
dcf_estimate |
Simplified DCF intrinsic value with margin of safety |
Resources
| URI | Description |
|---|---|
market://overview |
Major US indices (S&P 500, NASDAQ, Dow, VIX, 10Y Treasury) |
market://sectors |
Daily performance of 11 GICS sectors via SPDR ETFs |
Quickstart (local / stdio)
# 1. Clone and install
git clone https://github.com/YOUR_USERNAME/MCP-Server-Financial-Analyzer.git
cd MCP-Server-Financial-Analyzer
pip install uv
uv sync
# 2. Configure environment
cp .env.example .env
# Edit .env — set EDGAR_IDENTITY to "Your Name your@email.com"
# 3. Run (stdio mode for local use)
uv run financial-analyzer
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"financial-analyzer": {
"command": "uv",
"args": ["run", "--directory", "/path/to/MCP-Server-Financial-Analyzer", "financial-analyzer"],
"env": {
"EDGAR_IDENTITY": "Your Name your@email.com"
}
}
}
}
VS Code (Copilot)
Add to .vscode/mcp.json or user settings:
{
"servers": {
"financial-analyzer": {
"type": "stdio",
"command": "uv",
"args": ["run", "--directory", "/path/to/MCP-Server-Financial-Analyzer", "financial-analyzer"],
"env": {
"EDGAR_IDENTITY": "Your Name your@email.com"
}
}
}
}
Deploy to Render
This repo includes a render.yaml for one-click deployment.
- Push to GitHub
- Go to render.com → New → Blueprint → connect your repo
- Set
EDGAR_IDENTITYto your real name and email in the Render dashboard - Deploy — your MCP endpoint will be at
https://<service-name>.onrender.com/mcp
Connect remote clients to the deployed server
{
"mcpServers": {
"financial-analyzer": {
"type": "http",
"url": "https://<service-name>.onrender.com/mcp",
"headers": {
"Authorization": "Bearer <MCP_AUTH_TOKEN>"
}
}
}
}
The MCP_AUTH_TOKEN is auto-generated by Render and visible in your service's environment variables.
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
EDGAR_IDENTITY |
Yes | — | "Name email" per SEC fair-use policy |
TRANSPORT |
No | stdio |
stdio for local, streamable-http for cloud |
HOST |
No | 0.0.0.0 |
Bind address (HTTP mode only) |
PORT |
No | 8000 |
Port (HTTP mode only) |
MCP_AUTH_TOKEN |
No | — | Bearer token to protect the HTTP endpoint |
Disclaimer
This server provides financial data for informational and educational purposes only. It is not financial advice. Always verify data from authoritative sources before making investment decisions.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。