Wellness Pulse
WellPulse MCP is a privacy-first AI layer that transforms wellbeing data into real-time insights, benchmarks, and actionable summaries for faster decision-making.
README
Wellness Pulse MCP
Plug your AI into real wellbeing intelligence.
One connection gives your AI credible public benchmarks (CDC PLACES) plus institution-specific wellness signals — trends, snapshots, and alert checks — from your WellPulse data, returned in plain JSON.
Why teams add this
| Instant narrative | Your AI can explain "what changed" without a human analyst |
| Benchmarks that sell | CDC county mental distress context for marketing and reports |
| Institution signals | Daily trends + alert checks to catch issues early |
| One integration | Add the MCP once; reuse across copilots, agents, dashboards |
How it works
AI app / agent
│ (MCP tools)
▼
WellPulse MCP (this server)
├─ Public benchmarks (CDC PLACES)
└─ Institution data (your DB)
▼
Plain-English insights + structured JSON
Designed for fast "ask → answer" loops in copilots and automations.
What you can ask
- "What's our wellness trend for the last 90 days?"
- "Did we drop week-over-week? Why might that matter?"
- "What's the CDC mental distress benchmark for this ZIP?"
- "Write a short exec update with numbers and context."
Available Tools
| Tool | Description |
|---|---|
get_mental_health_benchmark |
CDC PLACES frequent mental distress (FMD) for a zip or county_fips; returns scope, values, optional national_percentile_rank, and marketing_copy |
get_sector_snapshot |
Sector-level snapshot over a window; returns institutions_with_responses, total_responses, avg_wellness_score |
get_basic_alert_guidance |
Default alert thresholds by org_size and location_type |
get_institution_snapshot |
Counts, avg_wellness_score, last_response_at for an institution over a window |
get_institution_trend_daily |
Daily series of { day, avg_wellness, responses } |
get_institution_alert_check |
Compares last 7d vs prior 7d; returns drop_pct and alert flag |
Endpoints
| Transport | URL |
|---|---|
| HTTP Stream | https://wellpulse.org/mcp |
| SSE | https://wellpulse.org/sse |
Use JSON-RPC. For HTTP streaming, include: Accept: application/json, text/event-stream
Quickstart (cURL)
1 — Initialize session
curl -s https://wellpulse.org/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "initialize",
"params": {
"protocolVersion": "2025-03-26",
"capabilities": {},
"clientInfo": { "name": "example", "version": "1.0.0" }
}
}'
Capture the mcp-session-id response header for subsequent calls.
2 — List tools
curl -s https://wellpulse.org/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-H "mcp-session-id: <SESSION_ID>" \
-d '{ "jsonrpc": "2.0", "id": 2, "method": "tools/list", "params": {} }'
3 — Call a tool
curl -s https://wellpulse.org/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-H "mcp-session-id: <SESSION_ID>" \
-d '{
"jsonrpc": "2.0",
"id": 3,
"method": "tools/call",
"params": {
"name": "get_mental_health_benchmark",
"arguments": { "zip": "94597" }
}
}'
Running locally
Prerequisites
- Node.js 18+
- PostgreSQL database with the WellPulse schema (
pulseschema,search_pathset accordingly)
Setup
# 1. Install dependencies
npm install
# 2. Configure environment
cp .env.example .env
# Edit .env with your real DB credentials and preferred port
# 3. Start the server
npm start
The server starts at http://localhost:8383 by default (configurable via MCP_PORT in .env).
Environment variables
| Variable | Description | Default |
|---|---|---|
DB_HOST |
PostgreSQL host | localhost |
DB_PORT |
PostgreSQL port | 5432 |
DB_NAME |
Database name | (required) |
DB_USER |
Database user | (required) |
DB_PASSWORD |
Database password | (required) |
MCP_PORT |
Port the MCP server listens on | 8383 |
Project structure
wellpulse-mcp/
├── .env.example ← environment variable template
├── .gitignore
├── package.json
└── src/
├── index.js ← entry point
├── db.js ← shared PostgreSQL pool
└── tools/
├── mentalHealthBenchmark.js
├── sectorSnapshot.js
├── basicAlertGuidance.js
├── institutionSnapshot.js
├── institutionTrendDaily.js
└── institutionAlertCheck.js
Notes
- ZIP codes are resolved to county FIPS automatically via public APIs (zippopotam.us + FCC).
- If county-level CDC data is unavailable, responses include a national fallback with
scope: "national_fallback". - Institution tools require a valid
institution_idpresent in your database.
© 2026 Wellness Pulse
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.
E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.