Healthchecks.io MCP server
Healthchecks.io in any MCP client, through Memtro: Healthchecks.io does not publish this server. Memtro's Healthchecks.io connector reads Healthchecks.io through its API with the credentials you connect, and one endpoint hands those tools, every other system you connect and Memtro's memory tools to Claude Code, Cursor, Claude Desktop or anything else that speaks Streamable HTTP, as you.
What the model can do
Healthchecks.io cron and heartbeat monitoring, hosted or self-hosted: one project's checks with their status (up, late, down, paused), last and next expected ping, schedule and tags, each check's history of going down and coming back up, its recent pings, and the project's integrations by name. Can create, change, pause, resume and delete checks, each only when asked.
Reads
healthchecks_list_checksChecks in the Healthchecks project: name, slug, tags, status (new, up, grace = late, down, paused), last ping, next expected ping…healthchecks_get_checkOne Healthchecks check by its id (the uuid, or the unique_key a read-only key sees): status, last and next ping, schedule, grace period…healthchecks_check_flipsA Healthchecks check's status changes (flips): each time it went down or came back up, newest first, with how many downs there were.healthchecks_check_pingsA Healthchecks check's most recent pings, newest first: type (success, start, fail, log, ign), time, sequence number…healthchecks_list_integrationsThe Healthchecks project's notification integrations (email, Slack, SMS, webhook ...): id, name and kind.
Acts, when you ask
These change something in Healthchecks.io. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.
healthchecks_create_checkCreate a check in the Healthchecks project.healthchecks_update_checkChange a Healthchecks check: name, slug, tags (replaces them all), schedule or period, time zone, grace period, description, manual resume…healthchecks_pause_checkPause a Healthchecks check.healthchecks_resume_checkResume a paused Healthchecks check.healthchecks_delete_checkDelete a Healthchecks check.
Connect it
First connect Healthchecks.io on Dashboard → Connections, then add Memtro to your client once. The Healthchecks.io tools appear alongside the tools of everything else you have connected; nothing is configured per connector.
Claude Code
The Memtro plugin registers the server and a skill for when to use it; the tools are then available in every session.
claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...Cursor
Add the server to .cursor/mcp.json in the project, or to the global file under ~/.cursor/.
{
"mcpServers": {
"memtro": {
"url": "https://platform.memtro.com/api/mcp",
"headers": {
"Authorization": "Bearer sk-memtro-..."
}
}
}
}Claude Desktop
Create a personal API key on Dashboard → Profile → API keys. In Claude Desktop add an MCP server of type HTTP with URL https://platform.memtro.com/api/mcp and the header Authorization: Bearer sk-memtro-…
OpenCode
A remote server in opencode.json.
{
"mcp": {
"memtro": {
"type": "remote",
"url": "https://platform.memtro.com/api/mcp",
"headers": {
"Authorization": "Bearer sk-memtro-..."
}
}
}
}Pi
One command: pi mcp add memtro --url https://platform.memtro.com/api/mcp --bearer-token-env-var MEMTRO_API_KEY. Tools arrive as mcp__memtro__*. The pi-memtro extension registers it for you, alongside Memtro as the model.
Any other client
Add an MCP server of type HTTP (Streamable HTTP, stateless) at https://platform.memtro.com/api/mcp with the header Authorization: Bearer sk-memtro-.... Codex, Zed, Windsurf, Cline and the SDKs all take a remote server this way.
Who may use it
The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared Healthchecks.io connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.
Ask it like this
- › Is anything down?
- › When did the nightly backup job last run?
- › How often did the billing export fail this month?
- › Which checks are paused?
- › Pause the report job check until the migration is done
Questions
- Is this an official Healthchecks.io MCP server?
- No. It is Memtro's MCP server with Memtro's Healthchecks.io connector behind it: the connector reads Healthchecks.io through its API with the credentials you connect on Dashboard → Connections, and Healthchecks.io publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.
- What does it cost?
- Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.
- Can it change anything in Healthchecks.io?
- Only when you ask, and only what it has been granted: create a check (it alerts nobody unless told to use every integration); change a check's name, slug, tags, schedule, grace period or integrations; pause a check's monitoring (no alerts fire while paused); resume a paused check; delete a check (permanent). Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.
- Which clients work?
- Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.