alphastream
alphastream 是一个由 AI 驱动的投资决策平台，通过多 Agent 协同编排系统，实时流式输出覆盖全球金融市场的深度洞察。基于 LangGraph 和 Python 构建，它无缝整合技术指标、基本面数据、资金流向分析和情绪智能，形成动态自适应的工作流。不同于传统的回测工具，alphastream 通过 SSE 将完整的决策过程——从数据获取、工具调用到最终推理——全程可视化，为投资者提供透明的可执行智能。
Alphastream MCP server provides AI agents with comprehensive access to global financial market data, including A-shares, U.S. stocks, ETFs, and indices through a standardized Model Context Protocol interface. Built on Python and Flask, it integrates 21 data adapters with automatic fallback routing across sources like AKShare, BaoStock, SEC EDGAR, FRED, and Yahoo Finance, delivering technical indicators, fundamental analysis, capital flow data, and sentiment intelligence. The server supports 70+ financial tools that agents can invoke via function calling to retrieve real-time quotes, historical K-line data, financial statements, valuation metrics, and macro-economic indicators. Designed for LangGraph multi-agent systems, it enables transparent, streaming decision workflows with Server-Sent Events for progress visualization.
Key Features
Use Cases
- 01Building AI investment advisors that analyze stocks across multiple global markets
- 02Integrating financial data streams into LangGraph multi-agent trading systems
- 03Providing real-time market data and technical analysis to conversational AI assistants
- 04Automating fundamental analysis and valuation comparisons for portfolio management agents
- 05Enabling sentiment analysis agents to correlate news flow with price movements
- 06Creating agent-driven financial research workflows with transparent reasoning chains
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
alphastream — FAQ
What is the alphastream MCP server?+
It's a Model Context Protocol server that exposes 70+ financial data tools to AI agents, providing standardized access to global stock market data, technical indicators, fundamentals, and news across 21 data sources with automatic fallback.
How do I install and run the MCP server?+
Clone the repository, install Python dependencies with pip install -r requirements.txt, configure environment variables in .env (minimum: OpenAI API URL/key), then run python3 run.py or use Docker Compose with docker compose up -d.
Which AI clients work with this MCP server?+
It integrates with any LangGraph or LangChain-based system and supports OpenAI SDK-compatible clients. The server exposes a standard REST API and SSE streams that can be consumed by custom agents or the included Next.js frontend.
Do I need API keys to use this server?+
An OpenAI-compatible LLM API key is required (DeepSeek, OpenAI, etc.). Optional keys like SERP_API_KEY, TAVILY_API_KEY, FRED_API_KEY, and SEC_EDGAR_UA enhance functionality but the server soft-degrades without them.
Is the alphastream MCP server free to use?+
Yes, the server code is open source. You'll incur costs only for LLM API usage and optional paid data sources like Wind if configured. Most data adapters use free sources like AKShare and BaoStock.
What data sources does it support?+
It includes 21 adapters covering AKShare and BaoStock for A-shares, SEC EDGAR for U.S. financials, FRED for macro data, yfinance for global quotes, plus alternative data like shipping indices, satellite imagery, corporate registries, job postings, and ESG metrics.
How do I install alphastream?+
Open the source repository on GitHub and follow its README. alphastream is a mcp server — MCP Agents Market links you directly to the official repo.
Is alphastream free?+
alphastream is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.