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
<div align="center">
<img src="https://raw.githubusercontent.com/prmail/WellPulse_mcp/main/WellPulse.jpeg" alt="WellPulse Logo" width="120" style="border-radius: 16px;" />
<h1>Wellness Pulse MCP</h1>
<p><strong>Plug your AI into real wellbeing intelligence β one connection, instant insight.</strong></p>
<p> <a href="https://wpulse.org/"><img src="https://img.shields.io/badge/Website-wpulse.org-0ea5e9?style=for-the-badge&logo=globe&logoColor=white" alt="Website" /></a> <a href="https://wpulse.org/mcp/"><img src="https://img.shields.io/badge/Status-Live-22c55e?style=for-the-badge&logo=statuspage&logoColor=white" alt="Status" /></a> <a href="https://claude.ai"><img src="https://img.shields.io/badge/Claude-Compatible-8b5cf6?style=for-the-badge&logo=anthropic&logoColor=white" alt="Claude" /></a> <a href="https://cursor.sh"><img src="https://img.shields.io/badge/Cursor-Compatible-3b82f6?style=for-the-badge&logo=cursor&logoColor=white" alt="Cursor" /></a> <a href="https://wpulse.org/"><img src="https://img.shields.io/badge/License-Institutional-1e3a5f?style=for-the-badge&logo=licenseplate&logoColor=white" alt="License" /></a> </p>
<p> <img src="https://img.shields.io/badge/Protocol-MCP%202025--03--26-f97316?style=for-the-badge" alt="MCP Protocol" /> <img src="https://img.shields.io/badge/Transport-HTTP%20Stream%20%7C%20SSE-ec4899?style=for-the-badge" alt="Transport" /> <img src="https://img.shields.io/badge/Data-CDC%20PLACES%20%2B%20Institutional-10b981?style=for-the-badge" alt="Data Sources" /> <img src="https://img.shields.io/badge/Privacy-No%20Tracking%20%7C%20No%20IDs-6366f1?style=for-the-badge&logo=shield&logoColor=white" alt="Privacy" /> </p>
<br />
Wellness Pulse MCP is a plug-and-play intelligence layer that turns raw wellbeing data into clear, actionable insights for AI systems.
One integration connects your copilots, agents, and dashboards to trusted public benchmarks and live institutional wellness signals β no analyst required.
</div>
π§ What Is Wellness Pulse MCP?
Wellness Pulse MCP is a Model Context Protocol (MCP) server that bridges the gap between raw wellbeing data and AI-powered understanding.
With a single integration, your AI gets access to:
- π CDC PLACES public benchmarks β trusted mental health data for any ZIP code or county in the US
- π’ Institutional wellness signals β live trends, snapshots, and alert checks from your organization's Wellness Pulse data
- π£οΈ Plain-English explanations β AI-ready summaries returned alongside structured JSON
Built for fast "ask β answer" workflows in copilots, automations, and AI dashboards β no human analysis needed in the loop.
β¨ Why Teams Add Wellness Pulse MCP
| Capability | What It Unlocks |
|---|---|
| π Instant Narrative | Your AI explains "what changed and why it matters" without a human analyst. |
| π CDC Benchmarks | County-level mental distress context for marketing decks, reports, and grant applications. |
| π‘ Live Institution Signals | Daily trends + alert checks that catch wellbeing drops before they become crises. |
| π One Integration | Add the MCP once β reuse it across every copilot, agent, and dashboard your team runs. |
| π Privacy-First | No user tracking. No identifiers. Trusted by institutions that take privacy seriously. |
ποΈ Architecture Overview

π οΈ Available Tools
π Public Benchmark Tools
get_mental_health_benchmark
Fetches CDC PLACES Frequent Mental Distress (FMD) data for a given ZIP code or county FIPS.
Arguments:
| Parameter | Type | Required | Description |
|---|---|---|---|
zip |
string | optional* | 5-digit US ZIP code |
county_fips |
string | optional* | County FIPS code |
At least one of zip or county_fips is required.
Returns: scope, values, national_percentile_rank (optional), marketing_copy
Example use case: "What's the CDC mental distress benchmark for ZIP 94597?"
get_basic_alert_guidance
Returns default alert thresholds based on organization size and location type β no institution ID needed.
Arguments:
| Parameter | Type | Required | Description |
|---|---|---|---|
org_size |
string | β | e.g. "small", "medium", "large" |
location_type |
string | β | e.g. "urban", "rural", "suburban" |
Example use case: "What alert thresholds should we use for a mid-size suburban institution?"
π’ Institution Data Tools
These tools require a valid institution identifier (
institution_id) from your Wellness Pulse account.
get_institution_snapshot
A point-in-time snapshot of wellness data for your institution over a given window.
Arguments:
| Parameter | Type | Required | Description |
|---|---|---|---|
institution_id |
string | β | Your Wellness Pulse institution ID |
window_days |
integer | β | Look-back window in days (e.g. 30, 90) |
Returns: response_count, avg_wellness_score, last_response_at
get_institution_trend_daily
Fetches a daily time-series of wellness scores and response counts.
Arguments:
| Parameter | Type | Required | Description |
|---|---|---|---|
institution_id |
string | β | Your Wellness Pulse institution ID |
window_days |
integer | β | Number of days to include |
Returns: Array of { day, avg_wellness, responses } objects
Example use case: "What's our wellness trend for the last 90 days?"
get_institution_alert_check
Compares last 7 days vs prior 7 days and flags significant drops.
Arguments:
| Parameter | Type | Required | Description |
|---|---|---|---|
institution_id |
string | β | Your Wellness Pulse institution ID |
Returns: drop_pct, alert (boolean flag)
Example use case: "Did we drop week-over-week? Should we be concerned?"
get_sector_snapshot
Sector-level aggregated wellness data across institutions.
Arguments:
| Parameter | Type | Required | Description |
|---|---|---|---|
sector |
string | β | Sector identifier |
window_days |
integer | β | Look-back window in days |
Returns: institutions_with_responses, total_responses, avg_wellness_score
π Getting Started
Step 1 β Add to Your AI Client
Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"Wellness Pulse": {
"url": "https://wpulse.org/mcp/",
"transport": "http-stream"
}
}
}
Cursor (.cursor/mcp.json)
{
"mcpServers": {
"Wellness Pulse": {
"url": "https://wpulse.org/mcp/",
"transport": "http-stream"
}
}
}
Step 2 β Initialize a Session (via cURL)
curl -s https://wpulse.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": "my-app", "version": "1.0.0" }
}
}'
π Capture the
mcp-session-idfrom the response headers β you'll need it for all subsequent calls.
Step 3 β List Available Tools
curl -s https://wpulse.org/mcp/ \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-H "mcp-session-id: <YOUR_SESSION_ID>" \
-d '{ "jsonrpc": "2.0", "id": 2, "method": "tools/list", "params": {} }'
Step 4 β Call a Tool
Example: Fetch CDC benchmark for a ZIP code
curl -s https://wpulse.org/mcp/ \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-H "mcp-session-id: <YOUR_SESSION_ID>" \
-d '{
"jsonrpc": "2.0",
"id": 3,
"method": "tools/call",
"params": {
"name": "get_mental_health_benchmark",
"arguments": { "zip": "94597" }
}
}'
Example: Check institution alert status
curl -s https://wpulse.org/mcp/ \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-H "mcp-session-id: <YOUR_SESSION_ID>" \
-d '{
"jsonrpc": "2.0",
"id": 4,
"method": "tools/call",
"params": {
"name": "get_institution_alert_check",
"arguments": { "institution_id": "inst_abc123" }
}
}'
π¬ Example Prompts to Ask Your AI
Once Wellness Pulse MCP is connected, try asking your AI:
"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 ZIP 94597?"
"Write a short exec update with our wellness numbers and CDC context."
"Are we above or below the national average for mental distress?"
"Flag any alert conditions in our institution data this week."
"Summarize the sector snapshot and highlight any outliers."
π Endpoints Reference
| Type | URL |
|---|---|
| HTTP Stream (canonical) | https://wpulse.org/mcp/ |
| HTTP Stream (redirect) | https://wpulse.org/mcp |
| SSE | https://wpulse.org/sse |
Required headers for HTTP Streaming:
Content-Type: application/json
Accept: application/json, text/event-stream
All calls use JSON-RPC 2.0.
π Privacy & Security
Wellness Pulse MCP is built with a privacy-first architecture:
- β No user tracking or behavioral logging
- β No personally identifiable information (PII) stored or transmitted
- β Institution data is scoped and access-controlled per account
- β All transport over HTTPS
- β Designed for compliance-conscious environments (healthcare, education, HR)
πΊοΈ Use Cases
π₯ Healthcare & Employee Wellness Teams
Use daily trend monitoring and week-over-week alert checks to detect emerging burnout or distress signals before they escalate β and give clinical or HR leadership an AI-generated executive summary on demand.
π Universities & Educational Institutions
Combine CDC county benchmarks with your student wellness survey data to contextualize scores relative to regional norms β ideal for accreditation reports and student affairs presentations.
π HR Tech & Wellness Platforms
Embed Wellness Pulse MCP into your existing copilot or dashboard product to instantly add benchmarked mental health context and trend narration β without building your own data pipeline.
π’ Public Health Communications
Pull CDC PLACES FMD data by ZIP or county to generate marketing copy, grant narratives, and community health reports grounded in authoritative public data.
π€ AI Agents & Automations
Wire Wellness Pulse MCP into multi-step agents that periodically check for alert conditions, draft stakeholder updates, and route escalations β all without human-in-the-loop analysis.
π Resources
- π Website: wpulse.org
- π MCP Protocol Docs: modelcontextprotocol.io
- π CDC PLACES Data: cdc.gov/places
- π Issues / Support: wpulse.org
π License
This server is available under an Institutional License. Please visit wpulse.org for licensing details and institutional access.
<div align="center">
<img src="https://raw.githubusercontent.com/prmail/WellPulse_mcp/main/WellPulse.jpeg" alt="WellPulse" width="60" />
<p>Built with care by the <strong>Wellness Pulse</strong> team.<br/>Helping organizations understand and act on wellbeing data β intelligently.</p>
<p> <a href="https://wpulse.org/">wpulse.org</a> β’ <a href="https://wpulse.org/mcp/">Live MCP Endpoint</a> </p>
</div>
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.