FinanceNews MCP
Enables AI assistants to search and retrieve real-time financial news from Finnhub via natural language queries.
README
š° FinanceNews MCP
A Model Context Protocol (MCP) server that provides financial news search capabilities. This server enables AI assistants to fetch and analyze financial news from various sources based on user queries.
⨠Features
- š Smart News Search: Query financial news with natural language
- š Real-time Updates: Get the latest financial news and market updates
- š Finnhub Integration: Fetches real-time news from Finnhub financial data platform (no fake data)
- š High Performance: Built with TypeScript and Express for optimal performance
- š§ Easy Integration: Simple MCP protocol implementation
š ļø Installation
Prerequisites
- Node.js 18.0.0 or higher
- npm or yarn package manager
Install from npm
npm install -g financenews-mcp
Install from source
git clone https://github.com/guangxiangdebizi/FinanceNews-MCP.git
cd FinanceNews-MCP
npm install
npm run build
š Quick Start
1. Start the MCP Server
# Using npm global install
financenews-mcp
# Or from source
npm run start:http
The server will start on http://localhost:3000 by default.
2. Configure Your AI Client
Add the following configuration to your MCP client (e.g., Claude Desktop):
{
"mcpServers": {
"financenews-mcp": {
"type": "streamableHttp",
"url": "http://localhost:3000/mcp",
"timeout": 600
}
}
}
3. Start Using
Once configured, you can ask your AI assistant to search for financial news:
- "Search for Apple earnings news"
- "Find news about Federal Reserve interest rates"
- "Get cryptocurrency market updates"
š§ Available Tools
get_financial_news
Fetches financial news based on a search query.
Parameters:
query(string, required): Search query for financial news topics
Example Usage:
{
"name": "get_financial_news",
"arguments": {
"query": "Tesla stock earnings"
}
}
š” API Endpoints
- MCP Endpoint:
POST /mcp- Main MCP protocol endpoint - Health Check:
GET /health- Server health status
š§ Configuration
Environment Variables
Create a .env file in the project root:
# Server Configuration
PORT=3000
NODE_ENV=development
# API Keys (for production use)
# NEWS_API_KEY=your_news_api_key
# ALPHA_VANTAGE_API_KEY=your_alpha_vantage_key
# Rate Limiting
RATE_LIMIT_WINDOW_MS=900000
RATE_LIMIT_MAX_REQUESTS=100
# Cache Configuration
CACHE_TTL_SECONDS=300
# Logging
LOG_LEVEL=info
Custom Port
PORT=8080 npm run start:http
š Finnhub API Configuration
Getting Your Finnhub API Key
To fetch real financial news, you need to configure a Finnhub API key:
- Finnhub (finnhub.io)
- Free tier: 60 requests/minute
- Sign up at: https://finnhub.io/register
- Get your API key from the dashboard after registration
Configuration Options
You have two ways to configure your Finnhub API key:
Option 1: Environment Variable (Recommended for personal use)
- Copy the environment template:
cp env-example.txt .env
- Edit the
.envfile and add your Finnhub API key:
FINNHUB_API_KEY=your_actual_finnhub_key
Option 2: MCP Headers (Recommended for shared/team use)
Add headers directly to your MCP client configuration. This is useful when you want different API keys for different clients or when you can't modify environment variables.
Claude Desktop Configuration:
{
"mcpServers": {
"financenews-mcp": {
"type": "streamableHttp",
"url": "http://localhost:3000/mcp",
"headers": {
"X-Finnhub-API-Key": "your_actual_finnhub_key"
}
}
}
}
Supported Header Names:
X-Finnhub-API-Key(recommended)X-API-KeyAuthorization: Bearer your_key(standard Bearer token format)
Error Handling
- API Key Missing: If no Finnhub API key is configured, the tool will display clear instructions on how to obtain and configure the API key
- No Results: If Finnhub API doesn't return any results for your query, the tool will suggest alternative search terms
- Network Errors: Any network or API errors will be clearly communicated with helpful troubleshooting information
The tool does not use sample or fake data - it only returns real news from Finnhub or clear error messages.
šļø Development
Setup Development Environment
git clone https://github.com/guangxiangdebizi/FinanceNews-MCP.git
cd FinanceNews-MCP
npm install
cp .env.example .env
Development Scripts
# Build the project
npm run build
# Start development server
npm run dev
# Start production server
npm run start:http
# Clean build directory
npm run clean
Project Structure
src/
āāā index.ts # MCP server main entry point
āāā tools/
āāā financial-news.ts # Financial news search tool
š Integration Examples
Claude Desktop
- Open Claude Desktop settings
- Navigate to "Developer" tab
- Add the MCP server configuration:
{
"mcpServers": {
"financenews-mcp": {
"type": "streamableHttp",
"url": "http://localhost:3000/mcp",
"headers": {
"X-Finnhub-API-Key": "your_actual_finnhub_key"
}
}
}
}
Custom Headers (Optional)
For authentication or tenant identification:
{
"mcpServers": {
"financenews-mcp": {
"type": "streamableHttp",
"url": "http://localhost:3000/mcp",
"headers": {
"Authorization": "Bearer YOUR_TOKEN",
"X-Tenant-Id": "your_tenant_id"
}
}
}
}
š Production Deployment
Docker
FROM node:18-alpine
WORKDIR /app
COPY package*.json ./
RUN npm ci --only=production
COPY build/ ./build/
EXPOSE 3000
CMD ["npm", "run", "start:http"]
PM2
npm install -g pm2
pm2 start build/index.js --name "financenews-mcp"
š¤ Contributing
We welcome contributions! Please see our Contributing Guidelines for details.
Development Workflow
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Make your changes and add tests
- Commit your changes:
git commit -m 'Add amazing feature' - Push to the branch:
git push origin feature/amazing-feature - Open a Pull Request
š License
This project is licensed under the Apache License 2.0 - see the LICENSE file for details.
šØāš» Author
Xingyu Chen
- š§ Email: guangxiangdebizi@gmail.com
- š LinkedIn: Xingyu Chen
- š GitHub: @guangxiangdebizi
- š¦ NPM: @xingyuchen
š Acknowledgments
- Model Context Protocol for the excellent protocol specification
- Anthropic for Claude and MCP development
- The open-source community for inspiration and contributions
š Roadmap
- [ ] Real-time news API integrations
- [ ] Advanced filtering and categorization
- [ ] Sentiment analysis for news articles
- [ ] Historical news data access
- [ ] Multi-language support
- [ ] News summarization capabilities
<div align="center"> <p>Made with ā¤ļø by <a href="https://github.com/guangxiangdebizi">Xingyu Chen</a></p> <p>ā Star this repo if you find it helpful!</p> </div>
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.