
StressZero MCP - Burnout Risk Scoring
io.github.gomessoaresemmanuel-cpuPublished by GitHub account gomessoaresemmanuel-cpuv1.0.1Updated Oct 24, 2026
Burnout risk scoring across 3 dimensions (physical, emotional, effectiveness)
Overview
Local MCP server that lets an assistant run self-reported burnout risk self-assessments across physical, emotional and effectiveness dimensions via the…
- What you can do
- Run a self-assessed burnout analysis across physical, emotional and effectiveness dimensions, returning an indicative score, level, contributing factors and prevention tips
- Perform a simplified three-score quick check suited to short chatbot conversations
- Generate a detailed self-assessment report with action plans (requires a paid Starter tier or above)
- Create a free API key for a user (500 calls per month)
- Read the service's OpenAPI specification as a resource and use a guided assessment questionnaire prompt in French or English
- When to use it
- Useful for coaching assistants, wellness chatbots, HR agents working with aggregated signals, or automation flows that want to offer a structured, self-reported workload and burnout check inside a conversation. It is not a medical or diagnostic tool.
- Requirements
- Runs locally via npx (Node.js) over stdio. Requires a StressZero API key supplied in the STRESSZERO_API_KEY environment variable, obtained by signing up on the provider's site; an optional STRESSZERO_API_URL can override the API base URL. Network access to the provider's API is needed. The detailed report tool needs a paid Starter tier or higher.
Installation
In SourceWeft
- Open StressZero MCP - Burnout Risk Scoring in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
StressZero MCP Server
MCP server for the StressZero Intelligence API — burnout prevention self-assessment for AI agents, across 3 dimensions (physical, emotional, effectiveness).
Enable Claude, Cursor, Windsurf, n8n, and any MCP-compatible client to help users self-assess their workload signals in real-time conversations.
⚠️ Not a medical device. All scores are indicative, based on self-reported answers. This server provides no diagnosis, no screening, and no clinical triage. Persistent exhaustion warrants a doctor — the tools say so in their outputs.
Tools
Resources
Prompts
Quick Start
1. Get your free API key
Visit stresszeroentrepreneur.fr/intelligence-api and sign up. Free tier: 500 calls/month, no credit card required.
2. Configure your MCP client
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
Claude Code
Add to .mcp.json at your project root or ~/.claude/mcp.json:
Cursor
Add to .cursor/mcp.json:
Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
3. Use it
Ask Claude: "Check my burnout risk. My sleep quality is 40/100, motivation is 55/100, and productivity is 35/100. I work 60 hours/week as an entrepreneur."
Claude will automatically call quick_burnout_check and return your score with recommendations.
Use Cases
- AI coaching assistant — Help users self-assess their workload in real-time during conversations
- HR AI agent — Aggregated, anonymized team load signals only (individual scores are never exposed to employers)
- Wellness chatbot — Suggest next steps based on self-reported load, including seeing a doctor when signals persist
- n8n automation — Trigger prevention workflows when a self-assessed score crosses a threshold
- Productivity tool — Monitor self-reported wellbeing and suggest breaks
API Tiers
Free tier: 500 calls/month, no credit card. Current paid tiers and pricing: stresszeroentrepreneur.fr/intelligence-api
Environment Variables
Development
Debug with the MCP Inspector:
License
MIT — Emmanuel Gomes Soares, StressZero Entrepreneur
Source: README.md at commit 30477fc
Tools
0Version history
1- v1.0.1LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts