Connect an AI agent
Point any MCP client at the UpCheck server with a project API key.
What you get
UpCheck ships a remote MCP server, so any Model Context Protocol client (Claude, or your own agent) can manage monitors on your behalf. Say "monitor my site" and the agent drives the rest. The server exposes five tools:
| Tool | What it does |
|---|---|
list_monitors | List your monitors with current status and 24h stats |
create_monitor | Create a monitor, only a URL is required |
update_monitor | Edit fields, including enabled: false to pause |
delete_monitor | Delete a monitor by id |
test_monitor | Run one check against a draft config without saving |
Endpoint
The server speaks stateless streamable HTTP (JSON-RPC 2.0 over POST), which every current MCP client supports:
https://upcheck-api-a.rekwiem.com/mcpGet an API key
Authentication is a Bearer project API key. Create one in your project's Settings under API keys; the key starts with upk_ and is shown once. Discovery calls work without auth, but every tool call needs the key.
Add it as a connector
In clients with a connector UI (like Claude), add a custom remote MCP server, paste the endpoint above, and set the Authorization header to your key. That is the whole setup.
Manual configuration
For clients configured by file, add the server to your MCP config:
{
"mcpServers": {
"upcheck": {
"type": "http",
"url": "https://upcheck-api-a.rekwiem.com/mcp",
"headers": { "Authorization": "Bearer upk_your_key" }
}
}
}Or register it from the Claude Code CLI:
claude mcp add --transport http upcheck \
https://upcheck-api-a.rekwiem.com/mcp \
--header "Authorization: Bearer upk_your_key"Scope and safety
A key binds to one project, so the agent can only touch that project's monitors. It can never create more keys or reach account settings. Give the key an expiry for throwaway experiments, and revoke it any time from Settings.
Free plan works too