oncallhealth-mcp
OfficialIt connects AI assistants to On-Call Health on-call burnout data, and in this configuration runs in Code Mode where three meta-tools expose the full analytics catalog.
Discover tools with
search— query the catalog by keyword, with optional tag filters, limits, and brief/detailed/full detail levels.Inspect schemas with
get_schema— fetch parameter schemas for specific tools before calling them.Chain calls with
execute— run sandboxed async Python usingawait call_tool(name, params)to combine multiple tool calls and return one final result, saving context on multi-step tasks.Underlying catalog (reachable through the meta-tools): validate integrations; list Rootly, GitHub, Slack, Jira and Linear integrations; see who is currently on call.
Run new burnout analyses (
analysis_run,analysis_start/analysis_status) or read the latest one (analysis_current,analysis_summary,analysis_results).Query member-level risk: at-risk members, safe responders who can take extra shifts, risk checks for specific Rootly user IDs, and day-by-day health for one member.
Access methodology and analysis metadata via MCP resources, and use
weekly_brief/investigate_responderprompts for guided reports.Scores run 0–100 (higher = more at risk) and inform staffing decisions, not medical diagnosis.
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., "@oncallhealth-mcp start a new burnout analysis for the last 30 days"
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.
oncallhealth-mcp
MCP server for On-Call Health burnout analysis. Connects AI assistants to your on-call data for workload insights.
Prerequisites
An On-Call Health account at oncallhealth.ai
An API key from oncallhealth.ai/settings/api-keys
Related MCP server: whoop-mcp-server
Installation
The server runs locally over stdio with uvx (no install step) and reads the API key from the ONCALLHEALTH_API_KEY environment variable. Pick your client:
Claude Code
claude mcp add oncallhealth --env ONCALLHEALTH_API_KEY=och_live_... -- uvx oncallhealth-mcpClaude Desktop
Add to claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json, Windows: %APPDATA%\Claude\claude_desktop_config.json):
{
"mcpServers": {
"oncallhealth": {
"command": "uvx",
"args": ["oncallhealth-mcp"],
"env": { "ONCALLHEALTH_API_KEY": "och_live_your_api_key_here" }
}
}
}Cursor
Add to .cursor/mcp.json in your project (or ~/.cursor/mcp.json for global):
{
"mcpServers": {
"oncallhealth": {
"command": "uvx",
"args": ["oncallhealth-mcp"],
"env": { "ONCALLHEALTH_API_KEY": "och_live_your_api_key_here" }
}
}
}VS Code / GitHub Copilot
Add to .vscode/mcp.json in your project:
{
"servers": {
"oncallhealth": {
"command": "uvx",
"args": ["oncallhealth-mcp"],
"env": { "ONCALLHEALTH_API_KEY": "och_live_your_api_key_here" }
}
}
}Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"oncallhealth": {
"command": "uvx",
"args": ["oncallhealth-mcp"],
"env": { "ONCALLHEALTH_API_KEY": "och_live_your_api_key_here" }
}
}
}Codex CLI
codex mcp add oncallhealth --env ONCALLHEALTH_API_KEY=och_live_... -- uvx oncallhealth-mcpGemini CLI
gemini mcp add oncallhealth -e ONCALLHEALTH_API_KEY=och_live_... uvx oncallhealth-mcpManual / other clients
pip install oncallhealth-mcp
export ONCALLHEALTH_API_KEY=och_live_...
oncallhealth-mcpOr run without installing: ONCALLHEALTH_API_KEY=och_live_... uvx oncallhealth-mcp.
Configuration
Variable | Required | Default | Description |
| Yes (stdio) | - | API key from oncallhealth.ai |
| No |
| API endpoint URL |
| No | off |
|
| No |
| Seconds between status checks inside |
| No | - | HTTP only: comma-separated host names that enable the Host/Origin DNS-rebinding guard |
Request timeouts, retries and circuit-breaker settings are also configurable; see oncallhealth_mcp/client/config.py.
Security note
Avoid committing API keys to version control. Use environment variables or a secrets manager instead of hardcoding keys in config files.
Protocol compatibility
The server implements MCP revision 2026-07-28 (stateless Streamable HTTP, Mcp-Method/Mcp-Name routing headers, cacheable list results, the Tasks extension) and negotiates older revisions per connection, so clients on the 2025 handshake-era protocol keep working. Every tool publishes annotations (read-only, idempotent, open-world) and a structured output schema. The deprecated HTTP+SSE transport is not served.
Tools
Start with validate_integrations, then analysis_current (or analysis_run for a fresh analysis), then analysis_summary and the member-level tools.
Tool | What it does |
| Check that every connected integration has valid credentials. |
| List connected Rootly, GitHub, Slack, Jira and Linear integrations. |
| Who is currently on call for a Rootly integration ( |
| Metadata of the most recent analysis (status, timestamps, config). |
| Start an analysis and wait for it: |
| Start an analysis without waiting. Poll with |
| Status and metadata of an analysis ( |
| Team averages, risk distribution, top five at-risk and healthiest members. |
| Full raw payload of a completed analysis (large; prefer the focused tools). |
| Members at or above |
| Members at or below |
| Risk check for specific |
| Day-by-day health, incident and after-hours breakdown for |
OCH scores run 0-100; higher means more at risk. Scores inform staffing decisions and are not a medical diagnosis.
Resources
URI | Content |
| Short description of the scoring methodology |
| Metadata of the most recent analysis (JSON) |
| Team summary of a completed analysis (JSON) |
Prompts
Prompt | Arguments | Purpose |
|
| Weekly on-call health brief with follow-up actions |
|
| Dig into one responder's trend and recommend shift changes |
Code Mode (optional)
With --code-mode or ONCALLHEALTH_CODE_MODE=1 the catalog is exposed through FastMCP Code Mode: three meta-tools (search, get_schema, execute) let an agent discover tools on demand and chain calls in a sandboxed Python snippet. It saves context when an agent needs many calls per task, at the cost of hiding the tool list, annotations and output schemas from clients that read them directly. Off by default.
CLI reference
usage: oncallhealth-mcp [-h] [--transport {stdio,http}] [--host HOST]
[--port PORT] [--code-mode] [-v] [--version]
options:
--transport {stdio,http} Transport to use (default: stdio)
--host HOST Host to bind to (http transport only, default: 127.0.0.1)
--port PORT Port to bind to (http transport only, default: 8000)
--code-mode Expose the catalog through Code Mode meta-tools
-v, --verbose Enable verbose logging
--version show program's version number and exitHosted deployment (Streamable HTTP)
oncallhealth-mcp --transport http (or the Docker image, which runs uvicorn oncallhealth_mcp.transport:mcp_http_app) serves:
POST /mcp: stateless Streamable HTTP MCP endpointGET /health: unauthenticated health check
Every MCP request must carry the user's API key as Authorization: Bearer och_...; X-API-Key: och_... is accepted as well. Keys are verified against the On-Call Health API (successful checks are cached for five minutes) and unauthenticated requests get 401 before any tool runs. Tool calls are rate limited per key and per tool (for example analysis_run and analysis_start at 5/minute) identified from the JSON-RPC body, with 429 and Retry-After on excess.
Example remote client configuration (Claude Code):
claude mcp add --transport http oncallhealth https://your-host/mcp --header "Authorization: Bearer och_live_..."Because the server is stateless you can run several uvicorn workers or replicas. For analysis_run background tasks to be shared across workers, point FastMCP's task backend at Redis or Valkey with FASTMCP_DOCKET_URL; the default in-memory backend is per process.
Set ONCALLHEALTH_MCP_ALLOWED_HOSTS=mcp.example.com to enable FastMCP's Host/Origin DNS-rebinding guard for the public host name.
docker build -t oncallhealth-mcp .
docker run -p 8080:8080 oncallhealth-mcpLinks
On-Call Health - Main website
API Documentation - REST API docs
GitHub Issues - Report bugs
License
Apache-2.0
Available Tools
3 toolsexecuteB
Chain await call_tool(...) calls in one Python block; prefer returning the final answer from a single block.
Use return to produce output.
Only call_tool(tool_name: str, params: dict) -> Any is available in scope.
Inputs: code (required).
get_schemaA
Get parameter schemas for specific tools.
Use after searching to get the detail needed to call a tool.
Inputs: tools (required), detail. Returns: result
searchA
Search for available tools by query.
Returns matching tools ranked by relevance.
Inputs: query (required), tags, detail, limit. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: execute chains calls, get_schema retrieves parameter details, and search finds tools. There is no overlap or ambiguity.
Tool names are imperative verbs (execute, search) and one uses get_ prefix (get_schema). While mostly consistent, the underscore in get_schema differs from the others, causing a minor deviation.
With only 3 tools, the server feels underdeveloped for the domain implied by 'oncallhealth'. The tools are generic meta-tools rather than domain-specific actions, making the count too low for its apparent scope.
The tool set is severely incomplete for an oncall health server. It lacks any domain-specific tools (e.g., managing incidents, schedules, alerts) and only provides generic utility functions, failing to cover the intended domain.
Maintenance
Related MCP Connectors
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
MCP server for Uptrack uptime monitoring. Manage monitors and incidents from AI agents.
Hosted MCP server for Cliniko — patients, appointments, availability, and invoices for AI agents.
MCP server for Sentry - error monitoring, issue tracking, and debugging for AI assistants
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceMCP server that connects AI assistants like Claude to WHOOP health data, enabling natural language queries about recovery, sleep, workouts, and more.331 npm181MIT
- AlicenseAqualityDmaintenanceMCP server that enables AI assistants to access Whoop health data including recovery, sleep, workouts, and daily strain for personalized health recommendations.7MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP server that enables AI assistants to access Oura Ring health data including activity, sleep, heart rate, stress, and personal info.2-
- FlicenseNot gradedqualityDmaintenanceSelf-hosted MCP server that provides read-only access to Google Health API v4, enabling analysis of personal health data via OpenAI Responses API or ChatGPT.-