healthchecksio-mcp
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., "@healthchecksio-mcp list my checks that are currently down"
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.
healthchecksio-mcp
π¬π§ English Β· π»π³ TiαΊΏng Viα»t
MCP server for the Healthchecks.io API. Lets Claude manage checks, channels, badges, and send pings.
Install (dev)
pnpm install
pnpm run build(npm also works: npm install && npm run build)
Related MCP server: uptrack-mcp
Env config
HEALTHCHECKS_API_KEY(required) β API key from Settings > API Access on healthchecks.io.HEALTHCHECKS_API_URL(optional) β defaults tohttps://healthchecks.io/api/v3. Change if self-hosting.HEALTHCHECKS_PING_URL(optional) β defaults tohttps://hc-ping.com. Change if self-hosting.
Register with Claude Code
Install straight from GitHub, no clone needed (pnpm preferred):
claude mcp add healthchecksio -e HEALTHCHECKS_API_KEY=your-key -- pnpm dlx github:nguyenhuy158/healthchecksio-mcpnpm also works:
claude mcp add healthchecksio -e HEALTHCHECKS_API_KEY=your-key -- npx -y github:nguyenhuy158/healthchecksio-mcpOr run from a local build, adding to .mcp.json / claude_desktop_config.json:
{
"mcpServers": {
"healthchecksio": {
"command": "node",
"args": ["/path/to/healthchecksio-mcp/build/index.js"],
"env": {
"HEALTHCHECKS_API_KEY": "your-key"
}
}
}
}Tools
list_checksβ list checks, filter by tag/statusget_checkβ get a single check's detailscreate_checkβ create a new checkupdate_checkβ update a checkpause_check/resume_checkdelete_checklist_check_flipsβ up/down status historylist_channelsβ notification channelslist_badgesβ badge URLspingβ send a heartbeat ping (success/fail/start/log)
Available Tools
11 toolscreate_checkCreate checkC
Create a new check.
Inputs: tz, desc, name, tags, +5 more.
delete_checkDelete checkB
Permanently delete a check.
Inputs: uuid (required).
get_checkGet checkA
Get details of a single check by its UUID.
Inputs: uuid (required).
list_badgesList badgesA
List status badge URLs for the project, per tag.
Inputs: no named parameters.
list_channelsList notification channelsA
List all notification channels (email, Slack, webhook, etc.) in the project.
Inputs: no named parameters.
list_check_flipsList check status flipsA
List status change history (up/down flips) for a check.
Inputs: uuid (required), seconds.
list_checksList checksA
List all checks in the project. Optionally filter by tag or status.
Inputs: tags, status.
pause_checkPause checkB
Pause monitoring for a check.
Inputs: uuid (required).
pingSend pingA
Send a ping (heartbeat) signal for a check. Use this to report success, failure, or manually test a check.
Inputs: uuid (required), state, message, exitStatus.
resume_checkResume checkA
Resume monitoring for a paused check (cron/schedule based checks only).
Inputs: uuid (required).
update_checkUpdate checkC
Update an existing check's configuration.
Inputs: uuid (required), tz, desc, name, +5 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 11 tools
Each tool targets a specific resource and action: checks (CRUD, pause/resume, flips), channels, badges, and ping. No two tools have overlapping purposes, and actions like pause vs. resume are clearly distinct.
All tools follow a consistent verb_noun pattern in snake_case (list_checks, get_check, create_check, update_check, delete_check, pause_check, resume_check). The single exception 'ping' is a standard verb for heartbeats and fits the pattern.
11 tools is well-scoped for a health checks server. The set covers the primary resource (checks) with full lifecycle actions, plus supporting resources (channels, badges) and the ping action. No unnecessary bloat or thinness.
The check lifecycle is complete: create, read, update, delete, list, pause, resume. Additional operations like listing flips, channels, badges, and sending pings cover the core functionality of healthchecks.io with no obvious gaps.
Maintenance
Related MCP Connectors
Uptime, SSL, DNS and domain monitoring you can talk to from Claude or any MCP client.
Health checks for public MCP servers: status, latency, tools, and uptime.
MCP server for Uptrack uptime monitoring. Manage monitors and incidents from AI agents.
Pingstack monitors cron jobs and scheduled tasks with heartbeat checks, and checks websites, TCP ports, DNS records, SSL certificates and domain expiry. This MCP server lets your agent create, update, pause and delete checks, build dashboards and publish them as status pages, manage notification groups, and read incidents with their causes, uptime, run history and latency. Pause, delete and unpublish stay off until you turn them on. Browser sign-in, no API key needed.
Related MCP Servers
- AlicenseAqualityCmaintenanceMCP Server for the Notion API, enabling Claude to interact with Notion workspaces.311,700 npm924MIT

uptrack-mcpofficial
AlicenseNot gradedqualityCmaintenanceMCP server for Uptrack uptime monitoring. Manage monitors and incidents from AI agents like Claude, ChatGPT, and Cursor.13 npmMIT- FlicenseBqualityBmaintenanceMCP server for managing self-hosted Uptime Kuma monitors and querying uptime statistics from Claude.15-
- AlicenseAqualityDmaintenanceMCP server for Claude Code to interact with OpenClaw AI agents (Daemon, Soren, Ash, etc.) via the gateway API, providing tools to ask agents, list them, and check their status.3380 npmMIT