Slate MCP Server
Connects Technolutions Slate with Claude to query and analyze student enrollment demographics, diversity metrics, and enrollment funnel data through natural language.
README
Slate MCP Server
An MCP (Model Context Protocol) server that connects Technolutions Slate with Claude, enabling you to query and analyze student enrollment demographics data through natural language.
Features
- Enrollment Demographics: Get comprehensive demographic summaries for incoming classes
- Diversity Metrics: Calculate diversity indices, URM percentages, and geographic diversity
- Enrollment Funnel: Track conversion rates from prospect to enrolled
- Year-over-Year Comparisons: Analyze trends across multiple enrollment years
- Flexible Queries: Search and filter students by various criteria
Prerequisites
- Node.js 18.0.0 or higher
- Access to a Technolutions Slate instance with API credentials
- Slate queries configured for enrollment data (see Slate Configuration)
Installation
# Clone the repository
git clone https://github.com/your-org/slate-mcp-server.git
cd slate-mcp-server
# Install dependencies
npm install
# Build the project
npm run build
Configuration
Environment Variables
Copy .env.example to .env and configure your Slate credentials:
cp .env.example .env
Required environment variables:
| Variable | Description |
|---|---|
SLATE_BASE_URL |
Your Slate instance URL (e.g., https://yourschool.technolutions.net) |
SLATE_USERNAME |
Slate API username |
SLATE_PASSWORD |
Slate API password |
SLATE_API_KEY |
(Optional) API key if your instance uses key-based auth |
Claude Desktop Configuration
Add the server to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"slate": {
"command": "node",
"args": ["/path/to/slate-mcp-server/dist/index.js"],
"env": {
"SLATE_BASE_URL": "https://yourschool.technolutions.net",
"SLATE_USERNAME": "your_username",
"SLATE_PASSWORD": "your_password"
}
}
}
}
Slate Configuration
This MCP server expects certain queries to be configured in your Slate instance. Work with your Slate administrator to create these queries:
Required Queries
-
enrollment_demographics: Returns enrolled student data with demographics- Required fields:
id,first_name,last_name,email,gender,ethnicity,race,citizenship,first_generation,state,country,intended_major,entry_year,entry_term,enrollment_status
- Required fields:
-
enrollment_funnel: Returns funnel counts- Required fields:
prospects,inquiries,applicants,admitted,deposited,enrolled
- Required fields:
-
students_by_status: Returns students filtered by application status- Required fields: Same as
enrollment_demographics
- Required fields: Same as
Query Parameters
The server will pass these parameters to your queries:
entry_year: The enrollment year (e.g., 2024)entry_term: The enrollment term (e.g., "Fall")application_status: For status-based queries
Available Tools
get_enrollment_demographics
Get a comprehensive demographics summary for enrolled students.
Parameters:
entry_year(required): The entry year (e.g., 2024)entry_term(optional): The entry term (default: "Fall")
Example prompt: "Show me the demographics for Fall 2024 incoming class"
get_diversity_metrics
Get detailed diversity metrics including diversity index and URM percentages.
Parameters:
entry_year(required): The entry yearentry_term(optional): The entry term
Example prompt: "What are the diversity metrics for our 2024 freshman class?"
get_enrollment_funnel
Get enrollment funnel data with conversion rates.
Parameters:
entry_year(required): The entry yearentry_term(optional): The entry term
Example prompt: "Show me the enrollment funnel and yield rates for Fall 2024"
compare_enrollment_years
Compare demographics across multiple years.
Parameters:
years(required): Array of years to compare (e.g., [2022, 2023, 2024])entry_term(optional): The entry term
Example prompt: "Compare enrollment demographics from 2022 to 2024"
get_demographics_report
Generate a formatted, readable demographics report.
Parameters:
entry_year(required): The entry yearentry_term(optional): The entry term
Example prompt: "Generate a demographics report for Fall 2024"
get_demographics_by_category
Get enrollment breakdown by a specific category.
Parameters:
entry_year(required): The entry yearcategory(required): One of:gender,ethnicity,state,country,admit_type,major,college,first_generation,internationalentry_term(optional): The entry term
Example prompt: "Show me enrollment by state for Fall 2024"
search_students
Search for students matching specific criteria.
Parameters:
entry_year(optional): Filter by entry yearentry_term(optional): Filter by entry termstate(optional): Filter by home statecountry(optional): Filter by home countrymajor(optional): Filter by intended majorfirst_generation(optional): Filter by first-gen statusinternational(optional): Filter by international statuslimit(optional): Max results (default: 100)
Example prompt: "Find all first-generation students from California in Fall 2024"
Example Conversations
Getting Annual Demographics Report
User: What does our incoming Fall 2024 class look like demographically?
Claude: I'll pull the enrollment demographics for Fall 2024...
[Uses get_enrollment_demographics tool]
Here's a summary of your Fall 2024 incoming class:
- Total Enrolled: 2,450 students
- Gender: 54% Female, 45% Male, 1% Non-binary
- First Generation: 28% (686 students)
- International: 12% (294 students)
...
Year-over-Year Analysis
User: How has our diversity changed over the past 3 years?
Claude: I'll compare the demographics across 2022, 2023, and 2024...
[Uses compare_enrollment_years tool]
Here's the year-over-year comparison:
- First Generation: 24% → 26% → 28% (+4 points)
- International: 10% → 11% → 12% (+2 points)
- URM: 22% → 24% → 26% (+4 points)
...
Development
# Run in development mode
npm run dev
# Type check
npm run typecheck
# Lint
npm run lint
# Build
npm run build
Security Considerations
- Never commit
.envfiles containing credentials - Use read-only API credentials when possible
- The server anonymizes personally identifiable information in search results
- Consider implementing rate limiting for production use
License
MIT
Support
For issues with this MCP server, please open a GitHub issue.
For Slate-specific questions, contact Technolutions Support.
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.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
E2B
Using MCP to run code via e2b.