io.github.Rootly-AI-LabsPublished by GitHub account Rootly-AI-Labsv0.4.1Updated Nov 5, 2026
On-call burnout analysis: team risk summaries, at-risk responders, daily health trends.
The publisher's own server: Rootly
Connects an assistant to On-Call Health so it can run burnout-risk analyses and surface at-risk or healthy on-call responders.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Follow the launch instructions in the repository.
MCP server for On-Call Health burnout analysis. Connects AI assistants to your on-call data for workload insights.
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:
Add to claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json, Windows: %APPDATA%\Claude\claude_desktop_config.json):
Add to .cursor/mcp.json in your project (or ~/.cursor/mcp.json for global):
Add to .vscode/mcp.json in your project:
Add to ~/.codeium/windsurf/mcp_config.json:
Or run without installing: ONCALLHEALTH_API_KEY=och_live_... uvx oncallhealth-mcp.
Request timeouts, retries and circuit-breaker settings are also configurable; see oncallhealth_mcp/client/config.py.
Avoid committing API keys to version control. Use environment variables or a secrets manager instead of hardcoding keys in config files.
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.
Start with validate_integrations, then analysis_current (or analysis_run for a fresh analysis), then analysis_summary and the member-level tools.
OCH scores run 0-100; higher means more at risk. Scores inform staffing decisions and are not a medical diagnosis.
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.
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 checkEvery 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):
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.
Apache-2.0
Source: README.md at commit 918da0c
Validate Integrations
Check that every connected integration has valid credentials. Call this before starting an analysis. Returns per-integration validation status (GitHub, Slack, Jira, Linear) and an all_valid flag.
force_refreshIntegrations List
List connected integrations (Rootly, GitHub, Slack, Jira, Linear).
Takes no parameters.
Oncall Users
Get the users currently on call for a Rootly integration. Cross-reference the returned emails with analysis data (for example get_at_risk_users) to see whether anyone currently on call is at risk.
integration_idrequiredAnalysis Current
Get the most recent analysis for the current account. Returns metadata only (status, timestamps, configuration). Use analysis_summary with the returned id for the team overview.
Takes no parameters.
Analysis Run
Start a new health analysis, wait for it to finish, and return the summary. Runs as a background task for clients that support the MCP Tasks extension and inline otherwise. Progress messages report the analysis status while waiting. On timeout the analysis keeps running on the backend; use analysis_status with the reported analysis_id to pick it up later.
days_backintegration_idinclude_weekendswait_timeout_secondsAnalysis Start
Start a new health analysis without waiting for it. Poll analysis_status until status is "completed", then use analysis_summary. Prefer analysis_run when you want a single call that waits for the result.
days_backintegration_idinclude_weekendsAnalysis Status
Get the status and metadata of an analysis.
analysis_idrequiredAnalysis Summary
Get a condensed team summary of a completed analysis. Returns team averages, the risk-level distribution and the five most and least at-risk members. Use analysis_results only when you need every field.
analysis_idrequiredAnalysis Results
Get the full raw results for a completed analysis. WARNING: Returns complete data for 80+ members with ~40 fields each and may overwhelm a context window. Prefer analysis_summary, get_at_risk_users or member_daily_health unless you need every field.
analysis_idrequiredGet At Risk Users
Get users at or above a health-risk threshold with their external IDs. Use this to identify at-risk responders and correlate them with Rootly, PagerDuty, Slack or GitHub using the returned platform IDs. Results are sorted by OCH score, highest risk first.
analysis_idrequiredmin_och_scoreinclude_risk_levelsGet Safe Responders
Get users with low health risk who could take additional on-call shifts. Use this to find replacement responders when removing at-risk users from schedules. Results are sorted by OCH score, healthiest first.
limitanalysis_idrequiredmax_och_scoreCheck Users Risk
Check health risk for specific users by their Rootly user IDs. Use this after fetching a schedule from Rootly to see whether any scheduled responders are at risk. A user is at risk when their OCH score is at or above min_och_score or their risk level is medium or high.
analysis_idrequiredmin_och_scorerootly_user_idsrequiredMember Daily Health
Get the day-by-day health breakdown for one team member. Shows per-day health scores, incident counts and after-hours activity over the analysis period (only days with data are included).
analysis_idrequiredmember_emailrequired90% 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.
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
com.rootlyOfficial publisher
Rootly MCP server for incident management, on-call scheduling and incident analysis, usable as a hosted endpoint or a local Python process.
Published by GitHub account wyre-technology
Lets an assistant read and manage Rootly incidents, alerts, on-call schedules, and organization data through a decision-tree tool set.
Published by GitHub account WYRE-AI
Local MCP server for Rootly incident management, letting an assistant list, create, update and resolve incidents and alerts, and read on-call schedules and org.
Published by GitHub account Servosity
Unofficial local MCP server that gives an assistant typed Rootly incident, alert and on-call commands backed by a local SQLite mirror for offline analytics.
com.mcparmory
A locally run MCP server that connects an assistant to Rootly for managing incident alerts, events and workflows with custom automations.
claude mcp add oncallhealth --env ONCALLHEALTH_API_KEY=och_live_... -- uvx oncallhealth-mcp{ "mcpServers": { "oncallhealth": { "command": "uvx", "args": ["oncallhealth-mcp"], "env": { "ONCALLHEALTH_API_KEY": "och_live_your_api_key_here" } } }}{ "mcpServers": { "oncallhealth": { "command": "uvx", "args": ["oncallhealth-mcp"], "env": { "ONCALLHEALTH_API_KEY": "och_live_your_api_key_here" } } }}{ "servers": { "oncallhealth": { "command": "uvx", "args": ["oncallhealth-mcp"], "env": { "ONCALLHEALTH_API_KEY": "och_live_your_api_key_here" } } }}{ "mcpServers": { "oncallhealth": { "command": "uvx", "args": ["oncallhealth-mcp"], "env": { "ONCALLHEALTH_API_KEY": "och_live_your_api_key_here" } } }}codex mcp add oncallhealth --env ONCALLHEALTH_API_KEY=och_live_... -- uvx oncallhealth-mcpgemini mcp add oncallhealth -e ONCALLHEALTH_API_KEY=och_live_... uvx oncallhealth-mcppip install oncallhealth-mcpexport ONCALLHEALTH_API_KEY=och_live_...oncallhealth-mcpusage: 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 exitclaude mcp add --transport http oncallhealth https://your-host/mcp --header "Authorization: Bearer och_live_..."docker build -t oncallhealth-mcp .docker run -p 8080:8080 oncallhealth-mcp