Rice Stock Data Portal MCP Server
Enables querying Rice Business Stock Market Data Portal using natural language through Claude Desktop, allowing users to ask about financial ratios, stocks, and companies.
README
Rice Stock Data Portal - MCP Server
A Model Context Protocol (MCP) server that provides natural language access to Rice Business Stock Market Data Portal through Claude Desktop.
Quick Start
For Users
-
Install the MCP server:
npm install -g @kerryback/data-portal-mcp -
Get your access token from your Rice Data Portal instance
-
Configure Claude Desktop by adding to your config file:
{ "mcpServers": { "rice-stock-data": { "command": "npx", "args": ["@kerryback/data-portal-mcp"], "env": { "KOYEB_APP_URL": "https://your-app.koyeb.app", "MCP_ACCESS_TOKEN": "your_access_token_here" } } } } -
Start asking questions in Claude Desktop:
- "Show me Apple's financial ratios"
- "Find undervalued healthcare stocks"
- "What are the top technology companies by market cap?"
For Developers
This repository contains the MCP server implementation for the Rice Stock Data Portal. The server acts as a bridge between Claude Desktop and your deployed Flask application.
Features
- 🔒 Secure Token Storage - Access tokens stored in Claude Desktop configuration
- 💬 Natural Language Queries - Ask questions in plain English
- 📊 Real-time Data - Direct access to your MotherDuck financial database
- 🎓 University Integration - Designed for academic use with email verification
- âš¡ Fast Responses - Leverages existing OpenAI chat integration
Architecture
Claude Desktop → MCP Server → Flask App → MotherDuck Database
The MCP server forwards natural language queries to your Flask app's /chat endpoint, which uses OpenAI to understand the query and generate appropriate SQL.
Repository Structure
src/index.ts- Main TypeScript MCP server implementationpackage.json- NPM package configurationProcfile- Koyeb deployment configurationFINAL_MCP_README.md- Complete user documentationDEPLOYMENT.md- Deployment guide
Development
# Install dependencies
npm install
# Build TypeScript
npm run build
# Run locally
npm start
# Test with environment variables
KOYEB_APP_URL=http://localhost:5000 \
MCP_ACCESS_TOKEN=your_token \
npm start
Deployment
This MCP server can be deployed to Koyeb for remote access:
- Connect your GitHub repository to Koyeb
- Set environment variables in Koyeb dashboard
- Deploy using the provided
Procfile
See DEPLOYMENT.md for complete instructions.
Documentation
FINAL_MCP_README.md- Complete user guideDEPLOYMENT.md- Deployment instructionsclaude_desktop_config.json- Configuration example
Support
- Issues: GitHub Issues
- Main Portal: Rice Stock Data Portal
License
MIT License - See LICENSE file for details
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.