About Checkly MCP by usefulapi
Checkly MCP by usefulapi is a hosted server for querying Checkly synthetic monitoring data from MCP clients. It is for teams that need to inspect checks, results, alerts, reporting, and related monitoring configuration.
Key features
- 01List checks and check groups
- 02Inspect statuses and results
- 03Review alerts and reporting
- 04Access dashboards and monitoring settings
- 05Create variables and maintenance windows
Use cases
- 01Review synthetic check results
- 02Investigate check status and alerts
- 03Inspect dashboards and reporting
- 04Create a variable or maintenance window
MCP support
Exposes Checkly account, monitoring, reporting, and selected write tools to MCP clients through a hosted endpoint. Users provide a Checkly API key and account ID.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://checkly.usefulapi.io/mcpclaude mcp add --transport http io-usefulapi-checkly https://checkly.usefulapi.io/mcp{"mcpServers":{"io-usefulapi-checkly":{"type":"http","url":"https://checkly.usefulapi.io/mcp"}}}Open in Cursor{"servers":{"io-usefulapi-checkly":{"type":"http","url":"https://checkly.usefulapi.io/mcp"}}}Open in VS Code{"mcpServers":{"io-usefulapi-checkly":{"type":"http","url":"https://checkly.usefulapi.io/mcp"}}}{"mcpServers":{"io-usefulapi-checkly":{"serverUrl":"https://checkly.usefulapi.io/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
22This tool takes no parameters.
Details
From the project READMECheckly MCP by usefulapi
Query your Checkly synthetic monitoring from Claude, Cursor, or any MCP client. Hosted, no local install — connect with your Checkly API key.
Live endpoint: https://checkly.usefulapi.io/mcp · Homepage: https://usefulapi.io/checkly
Connect
- Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste
https://checkly.usefulapi.io/mcp. - Claude Code:
claude mcp add --transport http checkly https://checkly.usefulapi.io/mcp, then run/mcpto log in. - VS Code: Add to VS Code.
- Cursor and other clients: add the URL as a remote MCP server:
{
"mcpServers": {
"checkly": {
"url": "https://checkly.usefulapi.io/mcp"
}
}
}
Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your Checkly credentials.
Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/checkly/
On first connect you'll paste your Checkly API key (and account ID). It's validated, stored per-user, and scoped to you.
Tools
| Tool | Type | What it does |
|---|---|---|
checkly_get_account | read | Get current account |
checkly_list_checks | read | List checks |
checkly_get_check | read | Get a check |
checkly_list_check_groups | read | List check groups |
checkly_get_check_group | read | Get a check group |
checkly_list_check_statuses | read | List check statuses |
checkly_get_check_status | read | Get check status |
checkly_list_check_results | read | List check results |
checkly_get_check_result | read | Get a check result |
checkly_list_check_alerts | read | List check alerts |
checkly_get_check_alerts | read | Get alerts for a check |
checkly_get_reporting | read | Get reporting |
checkly_list_dashboards | read | List dashboards |
checkly_list_alert_channels | read | List alert channels |
checkly_list_maintenance_windows | read | List maintenance windows |
checkly_list_locations | read | List locations |
checkly_list_private_locations | read | List private locations |
checkly_list_snippets | read | List snippets |
checkly_list_variables | read | List variables |
checkly_list_runtimes | read | List runtimes |
checkly_create_variable | write | Create environment variable |
checkly_create_maintenance_window | write | Create maintenance window |
checkly_usage_status | meta | Usage status (free-tier meter) |
checkly_request_feature | meta | Request a missing feature |
checkly_upgrade | meta | Upgrade to Pro (unlimited*) |
checkly_cancel_subscription | meta | Cancel the Pro subscription |
read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.
Pricing
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Pro | $9/mo or $90/yr (2 months free) | Unlimited* |
*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this server only. Subscribe with checkly_upgrade (it returns a Stripe Checkout link). Cancel any time with checkly_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running checkly_upgrade before then undoes the cancel. Or write to [email protected].
License
MIT — see LICENSE. Documentation only; the server is hosted.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.