Finmcp Finance Mcp
About
Lightweight TypeScript Finance MCP server wrapping Yahoo Finance APIs. Plug real-time financial data — stocks, options, crypto, earnings — into any AI assistant. No API key. Works via stdio, Docker, or HTTP.
Details
- Author
- Steve-sy
- Downloads
- 233
- Categories
- Other, Finance
Jump to
- Real-time stock quotes via get_quote tool
- Options chain data with get_option_chain
- Latest market news with get_market_news
- Earnings information using get_earnings
- Ticker search via search_ticker
- Built-in market_overview prompt for AI conversations
- Works over stdio, Docker, or SSE transports
- No API key required
Install and run via npx -y @mcp/finmcp for stdio, or use Docker with docker run -i --rm mcp/Finmcp. For SSE transport, run npx -y @mcp/finmcp --transport sse --port 3001. Configure the server in your AI client (e.g., Claude Desktop) by adding the appropriate command or URL. No API key is needed.
Production-grade (Cloud) financial data infrastructure for AI assistants with enterprise-grade resilience, comprehensive data quality validation, and production-ready monitoring.
FinMCP ships with aDockerfileand is fully Docker-based, so it runs on any platform that supports containers — Railway, Render, Fly.io, DigitalOcean App Platform, a VPS, or anything else.
Easiest option — Railway (recommended for beginners):
- Sign up atrailway.com(referral link — gives you free credits)
- New Project →Deploy from GitHub repo→ pastehttps://github.com/Steve-sy/finmcp
- Railway auto-detects theDockerfileand builds + deploys automatically
- (Optional)AddYF_MCP_API_KEYin Railway'sVariablestab to protect your endpoint
- Go toSettings → Networking → Generate Domainto get your public URL
- Your MCP endpoint is live at:https://<your-app>.up.railway.app/mcp
Other platforms (Render, Fly.io, VPS, etc.):
Any platform that can run a Docker container works. Point it at this repo, and set the start command tonode dist/http.js. The server listens on thePORTenvironment variable (automatically injected by most platforms) and defaults to3333.
Optional: protect public deployments withYF_MCP_API_KEYand connect using...?key=YOUR_SECRET.
Customize -> Connectors -> Add custom connector: Name: FinMCP Remote MCP Server URL: your cloud https url: https://<!-- -->/mcp
Claude Desktop Integration (Local — npm)
Add to yourclaude_desktop_config.json:
{ "mcpServers": { "finmcp": { "command": "finmcp" } } }
Claude Desktop Integration (Local — Docker)
If you prefer Docker over installing Node.js, first build the image:
Then add to yourclaude_desktop_config.json:
{ "mcpServers": { "finmcp": { "command": "docker", "args": ["run", "-i", "--rm", "finmcp", "node", "dist/index.js"] } } }
Note:ChatGPT Desktop MCP support may vary — check its documentation for custom connector configuration.
{ "mcpServers": { "finmcp": { "command": "finmcp" } } }
- 15 Financial Data Tools: Stocks, options, crypto, forex, company intelligence, market sentiment
- Circuit Breaker Pattern: Automatic recovery from API failures
- Multi-Strategy Rate Limiting: Token bucket + adaptive + per-endpoint limiting
- Data Quality Scoring: Completeness and integrity validation
- Comprehensive Caching: Graceful fallback with high cache hit ratio (70-90%)
- Streaming HTTP Transport: Run locally or deploy to the cloud (Docker/Railway) for HTTPS access
- Optional API Key Auth: Protect public deployments withYF_MCP_API_KEY
- Enterprise Testing: Unit, integration, e2e, and chaos tests
- get_quote- Real-time quotes with quality reporting
- get_historical_prices- OHLCV data with date ranges
- get_historical_prices_multi- Batch historical data
- get_quote_summary- Comprehensive company overview
- get_balance_sheet- Assets, liabilities, equity
- get_income_statement- Revenue, expenses, net income
- get_cash_flow_statement- Operating, investing, financing cash flows
- get_earnings- Quarterly earnings with estimates
- get_analysis- Analyst recommendations and price targets
- get_major_holders- Institutional and insider ownership
- get_news- Latest articles with relevance scoring
- get_options- Options chains with Greeks
- get_trending_symbols- Top movers with volume metrics
- screener- Filter stocks by 12+ criteria
- get_crypto_quote- Cryptocurrency prices
- get_forex_quote- Currency pair exchange rates
For complete documentation including configuration, usage examples, architecture details, and best practices:
- Complete Tool Reference
- Usage Guide with Examples
- Configuration Guide
- Architecture Details
- Data Verification Status
{ "rateLimit": { "requestsPerMinute": 60, "requestsPerHour": 1500 }, "cache": { "ttlQuotes": 60000, "maxCacheSize": 1000 }, "circuitBreaker": { "failureThreshold": 5, "monitoringWindow": 60000, "successThreshold": 3 } }
For detailed configuration options, seeConfiguration Guide.
- GitHub Repository
- npm Package
- MCP Protocol
- Report Issues
MCP to interface with multiple blockchains, staking, DeFi, swap, bridging, wallet management, DCA, Limit Orders, Coin Lookup, Tracking and more.
Financial intelligence for AI agents — 31 tools across 8 data sources including regime, derivatives, stablecoin flows, momentum, macro, weather patterns, and political cycles.
Execute stock and crypto trades via Trade Agent
MCP server for Aave — lending pool data, reserve info, user positions, and liquidation thresholds.
Bitcoin-native MCP server for AI agents: BTC/STX wallets, DeFi yield, sBTC peg, NFTs, and x402 payments.
Provides real-time prices for assets like precious metals and cryptocurrencies.
EUR settlement for AI agents. USDC/EURC to EUR via SEPA Instant. Trust scoring (KYA 0-100), market data, crypto analytics, AI tools.
Full-lifecycle algorithmic trading: describe strategies in plain English, AI generates code, backtest on real data, deploy live to 10+ brokers. Stocks, options, crypto, futures. Free tier available.
Crypto prices, market data, and token metadata via CoinGecko.
Crypto prices, market caps, rankings, and token metadata via CoinMarketCap.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
