Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Rice Stock Data MCP Server Show me the latest earnings for Microsoft"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server for accessing Rice Business Stock Market Data Portal through Claude Desktop.
Natural language queries for stock market data
Access to comprehensive financial metrics and indicators
Rice University email verification for access control
Seamless integration with Claude Desktop
Related MCP server: Alpha Vantage MCP Server
You must have Node.js installed on your computer to use this MCP server.
Download Node.js: Visit nodejs.org and install the LTS version
Verify installation: Open terminal/command prompt and run:
node --version
npm --versionBoth commands should return version numbers.
Visit the Rice Business Stock Market Data Portal
Verify your Rice University email address
Copy your personal access token
Open Claude Desktop
Go to Settings → Developer → Edit Config
Add the following configuration to your claude_desktop_config.json:
{
"mcpServers": {
"rice-stock-data": {
"command": "npx",
"args": ["@kerryback/rice-stock-data"],
"env": {
"USER_ACCESS_TOKEN": "your_actual_access_token_here",
"APP_URL": "https://your-actual-data-portal.rice-business.org"
}
}
}
}Replace "your_actual_access_token_here" with your actual access token from Step 1 (keep the quotation marks)
Save the configuration file
Restart Claude Desktop
Once configured, you can ask Claude questions about stock market data:
"Show me tech stocks with PE under 20"
"What are Apple's financial ratios?"
"List healthcare companies by market cap"
"Get the latest earnings data for Microsoft"
"Compare revenue growth across FAANG stocks"
npm install
npm run buildnpm run start:mcpnpm startUSER_ACCESS_TOKEN - Your personal Rice Data Portal access token (required)
APP_URL - Data portal base URL (default: https://data-portal-mcp.rice-business.org)
PORT - Web server port (default: 8000, used for deployment only)
The web server provides these endpoints (for deployment):
GET / - Server information
GET /health - Health check endpoint
POST /chat - Query endpoint (requires token in request body)
Verify your access token is correct and hasn't expired
Ensure you've verified your Rice University email
Wait a moment before making additional queries
The API has rate limiting to ensure fair usage
Make sure you've restarted Claude Desktop after configuration
Check that the configuration JSON is valid (no syntax errors)
Verify the package name is correct: @kerryback/rice-stock-data
For issues or questions about:
MCP Server: Open an issue in this repository
Data Portal Access: Contact Rice Business IT support
Stock Data: Refer to the Rice Business Stock Market Data Portal documentation
MIT
Query Rice Stock Data Portal using natural language. Ask questions about stocks, financial metrics, sectors, or any market data.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Natural language query about stock market data (e.g., 'Show me tech stocks with PE under 20', 'What are Apple's financial ratios?', 'List healthcare companies by market cap') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavior. It only mentions natural language querying and topics, but does not state whether it is read-only, what it returns, or any constraints. This leaves the agent without insight into side effects, permissions, or output format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that front-loads the tool's purpose and elaborates briefly. No filler or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple single-parameter tool, the description is adequate for basic selection but lacks details on return behavior, which is critical since no output schema exists. It does not explain what the agent can expect from the query response.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema coverage is 100% with a well-described 'prompt' parameter including examples. The description adds context about allowed query topics but does not add new parameter-level details beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool queries the Rice Stock Data Portal using natural language, with explicit examples of query types (stocks, financial metrics, sectors). It uses a specific verb and resource, distinguishing it from generic tools despite no sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for natural language queries about stock data but does not explicitly state when not to use it or mention alternatives. Since there are no sibling tools, no exclusions are necessary, but it lacks explicit 'when to use' language.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.10query_dataScored across 1 tool
Only one tool exists, so there is no possibility of overlap or confusion. The tool's purpose is clear and singular.
The single tool name follows a clean verb_noun pattern (query_data), which is internally consistent and readable.
With just one tool, the server feels minimal. However, for a natural language query interface, a single comprehensive tool may be sufficient, placing it at the borderline of appropriateness.
The natural language query tool describes broad coverage of stocks, financial metrics, sectors, and market data, effectively addressing the entire domain without obvious dead ends.
9,900+ US equities, 64 years of prices, financials, technicals, and earnings. Ask in plain English.
Portfolio analytics + US-equity market research for AI clients. ChatGPT deep-research compat.
Provide AI assistants with real-time access to official SEC EDGAR filings and financial data. Enab…
Institutional financial data with SEC filing citations, for every AI agent. OAuth 2.1.
