Stock Research MCP Server

Stock Research MCP Server

Provides comprehensive stock intelligence and technical analysis by integrating Alpha Vantage and Finnhub data. It enables users to generate detailed research reports and retrieve real-time market metrics, indicators, and news sentiment.

Category
Visit Server

README

Stock Research MCP Server (Python)

Production-grade MCP server for stock intelligence with:

  • Alpha Vantage + Finnhub provider fallback
  • Deterministic indicators/metrics/scoring
  • Claude narrative analysis constrained to computed data
  • Dual MCP transport modes: stdio (Claude Desktop local) and http with selectable SSE/streamable endpoints (Render)

File Tree

mcp_server/
├── main.py
├── tools/
│   └── stock_tools.py
├── providers/
│   ├── base.py
│   ├── alpha_vantage.py
│   ├── finnhub.py
│   └── router.py
├── scoring/
│   └── engine.py
├── indicators/
│   └── technical.py
├── analysis/
│   ├── metrics.py
│   ├── signal_engine.py
│   └── claude_engine.py
├── schemas/
│   └── models.py
├── config/
│   └── settings.py
└── utils/
    ├── logging.py
    └── http.py

tests/
├── test_indicators.py
├── test_metrics.py
└── test_scoring.py

Requirements

  • Python 3.11+
  • API keys:
    • CLAUDE_API_KEY
    • ALPHA_VANTAGE_API_KEY
    • FINNHUB_API_KEY

Setup

python -m venv .venv
. .venv/Scripts/activate
pip install -r requirements.txt
copy .env.example .env

Run (Claude Desktop local via stdio)

Set in .env:

TRANSPORT_MODE=stdio

Run:

python -m mcp_server.main

Run (Render remote via HTTP)

Set in .env:

TRANSPORT_MODE=http
HTTP_TRANSPORT=sse  # or streamable
HOST=0.0.0.0
PORT=8000

Run:

python -m mcp_server.main

Tools

  • Existing research/report tools:
    • stock_research_report (primary)
    • analyze_stock
    • get_price
    • get_ohlcv
    • get_technicals
    • get_fundamentals
    • get_news_sentiment
  • Trading-style tools:
    • get_stock_price
    • get_quote
    • get_company_profile
    • get_candles
    • get_stock_news
    • get_rsi
    • get_macd
    • get_key_financials

Tests

pytest -q

Render Deployment

  1. Push repo to GitHub.
  2. Create a Render Web Service.
  3. Build command:
    • pip install -r requirements.txt
  4. Start command:
    • python -m mcp_server.main
  5. Environment variables:
    • TRANSPORT_MODE=http
    • HTTP_TRANSPORT=sse (or streamable)
    • HOST=0.0.0.0
    • PORT=8000
    • CLAUDE_API_KEY, ALPHA_VANTAGE_API_KEY, FINNHUB_API_KEY
  6. MCP endpoints:
    • SSE mode (HTTP_TRANSPORT=sse):
      • https://<render-service-domain>/sse
      • https://<render-service-domain>/messages/ (POST)
    • Streamable mode (HTTP_TRANSPORT=streamable):
      • https://<render-service-domain>/mcp
  7. Optional health check endpoint:
    • https://<render-service-domain>/health

Claude Desktop Config (local stdio)

Example MCP server entry:

{
  "mcpServers": {
    "stock-research": {
      "command": "python",
      "args": ["-m", "mcp_server.main"],
      "env": {
        "TRANSPORT_MODE": "stdio",
        "CLAUDE_API_KEY": "YOUR_KEY",
        "ALPHA_VANTAGE_API_KEY": "YOUR_KEY",
        "FINNHUB_API_KEY": "YOUR_KEY"
      }
    }
  }
}

Transport Notes

  • TRANSPORT_MODE=auto (default) auto-selects:
    • http when hosted (PORT or RENDER env present)
    • stdio locally
  • HTTP_TRANSPORT=sse uses:
    • GET /sse
    • POST /messages/
  • HTTP_TRANSPORT=streamable uses:
    • POST /mcp

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured