oncallhealth-mcp
MCP server for On-Call Health burnout analysis. Connects AI assistants to your on-call data for workload insights.
README
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
Installation
Pick your editor or client below and follow the instructions.
Claude Code
claude mcp add oncallhealth -e ONCALLHEALTH_API_KEY=och_live_... -- uvx oncallhealth-mcp
Claude Desktop
Add to your 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"
}
}
}
}
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"
}
}
}
}
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"
}
}
}
}
Manual / Other Clients
Install from PyPI:
pip install oncallhealth-mcp
Run the server:
export ONCALLHEALTH_API_KEY=och_live_...
oncallhealth-mcp
Or run without installing using uvx:
ONCALLHEALTH_API_KEY=och_live_... uvx oncallhealth-mcp
Configuration
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
ONCALLHEALTH_API_KEY |
Yes | - | API key from oncallhealth.ai |
ONCALLHEALTH_API_URL |
No | https://api.oncallhealth.ai |
API endpoint URL |
Security Note
Avoid committing API keys to version control. Use environment variables or a secrets manager instead of hardcoding keys in config files.
Available Tools
analysis_start
Start a new burnout analysis for your on-call data.
Parameters:
days_back(int, default: 30): Number of days to analyzeinclude_weekends(bool, default: true): Include weekend dataintegration_id(int, optional): Specific integration to analyze
analysis_status
Check the status of a running analysis.
Parameters:
analysis_id(int): ID of the analysis to check
analysis_results
Get full results for a completed analysis.
Parameters:
analysis_id(int): ID of the completed analysis
analysis_current
Get the most recent analysis for your account.
Parameters: None
integrations_list
List all connected integrations (Rootly, GitHub, Slack, Jira, Linear).
Parameters: None
Resources
oncallhealth://methodology
Provides a brief description of the On-Call Health methodology for measuring workload and burnout risk.
Prompts
weekly_brief
Template for generating a weekly on-call health summary.
Parameters:
team_name(str): Name of the team to summarize
CLI Reference
usage: oncallhealth-mcp [-h] [--transport {stdio,http}] [--host HOST]
[--port PORT] [-v] [--version]
options:
-h, --help show this help message and exit
--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)
-v, --verbose Enable verbose logging
--version show program's version number and exit
Transport Options
- stdio (default): Standard input/output transport. Used by Claude Desktop and most MCP clients.
- http: HTTP transport with Server-Sent Events. Useful for web-based clients or debugging.
Links
- On-Call Health - Main website
- API Documentation - REST API docs
- GitHub Issues - Report bugs
License
Apache-2.0
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。