Back to search
12happy-mcp
MCP serverGitHub
12happy MCP server: uptime monitoring from Claude, Cursor and VS Code
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/12happyhq--12happy-mcp)HTML
<a href="/listings/12happyhq--12happy-mcp"><img src="/api/listings/12happyhq--12happy-mcp/badge.svg" alt="findsafeskills safety rating" /></a>Install
i
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Claude Code
claude mcp add 12happy -e TWELVEHAPPY_API_KEY=mon_live_... -- npx -y 12happy-mcp
Claude Desktop
Add this to `claude_desktop_config.json` (Settings → Developer → Edit Config), then restart Claude:
{
"mcpServers": {
"12happy": {
"command": "npx",
"args": ["-y", "12happy-mcp"],
"env": { "TWELVEHAPPY_API_KEY": "mon_live_..." }
}
}
}Cursor
Add the same block to `~/.cursor/mcp.json`, or to `.cursor/mcp.json` in a project.
VS Code
Add this to `.vscode/mcp.json`. VS Code asks for the key once and stores it securely:
{
"inputs": [
{ "type": "promptString", "id": "twelvehappy-key", "description": "12happy API key", "password": true }
],
"servers": {
"12happy": {
"command": "npx",
"args": ["-y", "12happy-mcp"],
"env": { "TWELVEHAPPY_API_KEY": "${input:twelvehappy-key}" }
}
}
}What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 116 lines
- # 12happy MCP server
- Uptime monitoring you can talk to. This [Model Context Protocol](https://modelcontextprotocol.io) server connects [12happy](https://www.12hpy.com/) to Claude, Cursor, VS Code and any other MCP client, so you can ask:
- - "Is anything down right now?"
- - "Watch https://api.example.com/health every minute and alert the #ops Slack channel."
- - "Why did the checkout monitor fail last night, and from which regions?"
- - "What was our uptime and p95 response time for the API last month?"
- - "Silence alerts for 20 minutes while I deploy."
- - "Tell me if the nightly backup stops running."
- 12happy checks from the US, Europe and Israel, and opens an incident only when a quorum of regions agrees that something is down, so one flaky probe doesn't page you.
- ## What you need
- - A 12happy account on the **Pro or Agency plan**, which include API access. [Start free](https://app.12hpy.com/), then upgrade from the console.
- - An **API key**: in the [console](https://app.12hpy.com/), open **API keys** and choose **Create key**. Pick the scopes the assistant should have. A key with only the read scopes can't change anything.
- - Node.js 20 or later.
- ## Install
- ### Claude Code
- ```bash
- claude mcp add 12happy -e TWELVEHAPPY_API_KEY=mon_live_... -- npx -y 12happy-mcp
- ```
- ### Claude Desktop
- Add this to `claude_desktop_config.json` (Settings → Developer → Edit Config), then restart Claude:
- ```json
- {
- "mcpServers": {
- "12happy": {
- "command": "npx",
- "args": ["-y", "12happy-mcp"],
- "env": { "TWELVEHAPPY_API_KEY": "mon_live_..." }
- }
- }
- }
- ```
- ### Cursor
- Add the same block to `~/.cursor/mcp.json`, or to `.cursor/mcp.json` in a project.
- ### VS Code
- Add this to `.vscode/mcp.json`. VS Code asks for the key once and stores it securely:
- ```json
- {
- "inputs": [
- { "type": "promptString", "id": "twelvehappy-key", "description": "12happy API key", "password": true }
- ],
- "servers": {
- "12happy": {
- "command": "npx",
- "args": ["-y", "12happy-mcp"],
- "env": { "TWELVEHAPPY_API_KEY": "${input:twelvehappy-key}" }
- }
- }
- }
- ```
- ## Tools
- | Tool | What it does |
- |---|---|
- | `get_overview` | Monitors up, down, slow and paused; open incidents; uptime over N days |
- | `list_monitors` | All monitors, filterable by status or text |
- | `get_monitor` | One monitor's settings and latest results per region |
- | `get_uptime_report` | Uptime % and p50/p95/p99 response time for any period or region |
- | `list_incidents` | Outages and slowdowns, with cause and confirming regions |
- | `list_alert_channels` | Email, Slack, webhook, SMS and other channels, and their health |
- | `list_regions` | Where checks can run from |
- | `create_monitor` | Watch a URL, keyword, hostname (ping, DNS, SSL certificate) or TCP port, or a cron job by heartbeat: it returns the URL the job calls when it finishes |
- | `update_monitor` | Change target, interval, regions, keyword, timeout or slow threshold |
- | `pause_monitor` | Pause or resume, keeping history |
- | `check_now` | Run a check immediately |
- | `delete_monitor` | Delete a monitor and its history (assistants are told to confirm first) |
- | `acknowledge_incident` | Take ownership and stop escalation |
- | `start_maintenance` | Silence alerts or pause checks for a deploy |
- | `set_monitor_alerts` | Choose which channels a monitor alerts, with escalation delays |
- Read-only tools are marked as such, and `delete_monitor` is marked destructive, so clients that ask before risky actions will ask.
- ## Settings
- | Variable | |
- |---|---|
- | `TWELVEHAPPY_API_KEY` | Required. A key from the console's API keys page. |
- | `TWELVEHAPPY_ORG` | Optional. Agencies and resellers: the client organization to act on by default. Every tool also takes an `organization` argument. |
- | `TWELVEHAPPY_API_URL` | Optional. Defaults to `https://be.12hpy.com/v1`. |
- ## Security
- - The key is sent only to the 12happy API, as a bearer token, and is never logged.
- - Scopes are enforced by the API: a key without `monitors:write` gets a clear "missing scope" error rather than a change.
- - Revoke a key at any time from the API keys page; it stops working immediately.
- ## Develop
- ```bash
- npm install
- npm run build
- npm run inspect # opens the MCP Inspector
- node --env-file=.env test/smoke.mjs <test-organization-id>
- ```
- The API reference is at [be.12hpy.com/docs/api](https://be.12hpy.com/docs/api).
- ## License
- MIT
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.