Checkly MCP tools

This reference reflects the current MCP Server v1 tool surface. It is not a roadmap or a commitment to future tools. Each tool is shown only when the MCP session has the required permission. Your account role and permissions must also allow the action. See security and permissions.

Account tools

Tool	Type	Description
`whoami`	Read	Return the authenticated user and account memberships visible to the MCP session.
`get-account-entitlements`	Read	Return the resolved account plan and feature entitlement state.
`list-account-members`	Read	List account members and pending invites.
`invite-account-member`	Write	Invite a user to the resolved account. OAuth-only. Requires `members:create` and all permissions of the built-in role you give. Owner and custom role (beta) invitations are unsupported. Sends an invite email and is not idempotent.
`prepare-local-check-authoring`	Read	Return an account-aware runbook for creating, testing, and deploying check code with the local Checkly CLI.

Example prompts:

Prompt

Use Checkly to show which accounts I can access.

Prompt

Prepare the local Checkly CLI steps to create a browser check for checkout.

Check tools

Tool	Type	Description
`list-check-stats`	Read	Return a paginated, filterable list of checks with current pass, fail, and degraded status. Set `includeReliability` to also return availability, response-time percentiles, and ICMP latency or packet loss over a quick range.
`get-check`	Read	Return the full configuration of one check: schedule, locations, alert settings, and the type-specific configuration such as `request`, `script`, or `heartbeat`.
`get-check-type-schema`	Read	Return the JSON Schema of the `check` payload for one check type, for either the create or the update operation.
`create-check`	Write	Create a check of any supported type from a JSON configuration. The check is created standalone, outside any Checkly CLI project.
`update-check`	Write	Update shared check properties such as name, tags, activation, or mute state, or pass a partial type-specific configuration. Does not trigger a check run.
`delete-check`	Write	Permanently delete a check, including its configuration and result history. Cannot be undone and requires confirmation.
`list-check-results`	Read	List recent compact results for one check, including HTTP response status and assertion counts when available. Raw logs, traces, screenshots, videos, and download URLs are omitted.
`get-check-result`	Read	Return compact detail for one check result.
`get-check-performance-summary`	Read	Return average, P50, P95, and P99 response-time metrics for one check over a date range when data is available.
`trigger-checks`	Write	Run existing deployed checks on demand and record the run as a test session. Consumes check-run execution quota.

List and filter checks

For large accounts, start with list-check-stats filters instead of asking for every check at once. The default response is status-only. The tool supports:

tag: filter by one or more tags.
type or checkType: filter by check type.
search: filter by check name.
status: filter by passing, failing, or degraded.
limit and page: page through matching checks. The default page size is 25 and the maximum is 100.
includeReliability: set to true to include availability, response-time percentiles, and ICMP latency or packet-loss metrics.
range: set the analytics range when includeReliability is true. The default is last24Hours.

The response includes pagination metadata (length, total, page, limit, and totalPages) plus the applied filters, so your client can continue with the next page only when needed. list-check-results stays compact for fast triage. Result rows include responseStatusCode, responseStatusText, totalAssertions, and failingAssertions when available, so your client can inspect common URL and API failure signals before fetching full result details or assets.

Create, update, and delete checks

The check write tools manage checks from a JSON configuration, without a local project or a CLI deploy. They support these check types:

API checks
Browser checks and Multistep checks with a single inline script
Heartbeat monitors
URL, TCP, DNS, ICMP, traceroute, gRPC, and SSL monitors

A typical create flow:

Call get-check-type-schema with the checkType to learn the check payload. Every check type takes different configuration, for example request for API checks and uptime monitors, script for browser checks, and heartbeat for heartbeat monitors.
Optionally call list-alert-channels to pick specific alert channels, and list-check-groups to find a groupId.
Call create-check with checkType and the check payload. By default the new check is subscribed to all of the account’s alert channels. Set autoAssignAlerts to false or pass check.alertChannelSubscriptions to change this.

When updating, update-check accepts either shared top-level properties (name, activated, muted, tags, useGlobalAlertSettings, runParallel, description, intent, aiAutoRepairEnabled) or a partial check object validated against the update schema for the check’s type. The two cannot be combined in one call. Array fields such as locations and tags replace the check’s current values.

delete-check permanently removes the check and its result history. The tool first returns a confirmation handle, and the deletion only proceeds when your client passes that handle back after you explicitly agree. To stop a check from running while keeping it, use update-check with activated: false instead.

Playwright Check Suites are managed as Monitoring as Code with the Checkly CLI. Use prepare-local-check-authoring for a CLI handoff. Changes made through MCP to a check that a CLI project manages are overwritten by that project’s next deploy. Example prompts:

Prompt

Show me the first page of failing API checks tagged production, then summarize what changed in their latest results.

Prompt

Create a URL monitor for https://www.example.com that runs every 5 minutes from eu-west-1 and us-east-1, tagged production.

Prompt

Update the "Checkout API" check to run every 10 minutes and add the tag critical. Keep all other settings.

Prompt

Trigger the checks tagged production-smoke, then poll the test session until results are available.

Interactive view tools

These read-only tools display interactive views in clients that support MCP Apps. They require the checkly:checks:read session permission and checks:read account permission.

Tool	Type	Description
`show-check-status`	Read	Display one check’s status card, with last-24-hour availability, P95, and P99 response times when available.
`show-check-list`	Read	Display a filtered check list with current status and up to 20 checks per page. Supports pagination without historical metrics.
`show-check-response-time`	Read	Display a response-time chart for one check. Defaults to the last 24 hours; custom past windows span at most seven days and must fall within your plan’s data retention.

Use these tools when you want a visual view in your conversation. For structured results, use list-check-stats or get-check-performance-summary.

Check group tools

Tool	Type	Description
`list-check-groups`	Read	List check groups with their check counts. Supports `search`, `tag`, `limit`, and `page` filters.
`get-check-group`	Read	Return the full configuration of one check group and the checks in it.
`create-check-group`	Write	Create a check group. Only `name` is required. By default the group is subscribed to all of the account’s alert channels.
`update-check-group`	Write	Change the settings of a check group. Fields left out keep their current values. List fields such as `tags`, `locations`, `alertChannelSubscriptions`, and `environmentVariables` are replaced as a whole.
`delete-check-group`	Write	Permanently delete a check group and every check in it. Cannot be undone and requires confirmation.

Group settings such as locations, alerting, retries, API check defaults, and environment variables apply to every check in the group. To put a check in a group, set groupId on the check with create-check or update-check. Example prompts:

Prompt

Create a check group named "Payments API" that runs from eu-central-1 and us-west-2 with a base URL of https://api.example.com, then move all checks tagged payments into it.

Alert channel tools

Tool	Type	Description
`list-alert-channels`	Read	List the account’s alert channels with the non-secret details that identify each one. Supports a `type` filter for `EMAIL`, `SLACK`, `SLACK_APP`, `WEBHOOK`, `SMS`, `PAGERDUTY`, `OPSGENIE`, and `CALL`.

Use the returned IDs to set alertChannelSubscriptions when creating or updating a check or check group. Example prompt:

Prompt

List my Slack alert channels, then subscribe the "Checkout API" check to the #incidents channel only.

Test session tools

Tool	Type	Description
`list-test-sessions`	Read	List recent test sessions with filters and cursor ordering.
`get-test-session`	Read	Return one test session and compact result rows.
`list-test-session-results`	Read	List compact result rows for one test session with bounded pagination and optional result filters.
`get-test-session-result`	Read	Return compact detail for one test-session result, including useful run metadata and small summaries.

Example prompt:

Prompt

Find the latest failed test session and show me the failed result IDs.

Result asset tools

Tool	Type	Description
`list-check-result-assets`	Read	Return a normalized asset manifest for a check result.
`fetch-check-result-asset`	Read	Fetch one selected check-result asset. Text assets may be returned inline with a byte limit; binary or large assets return a download link.
`list-test-session-result-assets`	Read	Return a normalized asset manifest for a test-session result.
`fetch-test-session-result-asset`	Read	Fetch one selected test-session-result asset. Text assets may be returned inline with a byte limit; binary or large assets return a download link.

Example prompt:

Prompt

For the failed check result, list available assets and fetch the text log if one exists.

Root cause analysis tools

Tool	Type	Description
`get-error-group-root-cause-analyses`	Read	Return a check or test-session error group and any existing root cause analyses.
`get-root-cause-analysis`	Read	Return one root cause analysis by RCA ID. Pending analyses return compact polling status.
`trigger-root-cause-analysis`	Write	Trigger a new RCA for a check or test-session error group. Requires run access and consumes RCA invocation quota.

Call get-error-group-root-cause-analyses before triggering a new RCA so your agent can reuse existing analysis when available. Example prompt:

Prompt

Check whether this error group already has an RCA. If it does not, ask me before triggering a new one.

Environment variable tools

Tool	Type	Description
`list-account-environment-variables`	Read	List account-level variables and secrets. Secret values are returned as `null`.
`get-account-environment-variable`	Read	Get one account-level variable by key. Secret values are returned as `null`.
`create-account-environment-variable`	Write	Create an account-level variable or secret. Secret values are encrypted and not echoed back.
`update-account-environment-variable`	Write	Update an account-level variable or secret by key. To update a secret, pass `secret: true`.

Example prompt:

Prompt

List account environment variables and tell me whether API_TOKEN is stored as a secret.

Status page tools

Tool	Type	Description
`list-status-pages`	Read	List status pages, including the cards and services (v2) or components (v3) needed for incident targeting.
`get-status-page`	Read	Get one status page with its cards and services (v2) or components (v3).

Example prompt:

Prompt

List my status pages and show the service IDs for the production page.

Incident tools

Tool	Type	Description
`list-status-page-incidents`	Read	List status page incidents, optionally filtered by page and incident status.
`get-status-page-incident`	Read	Get one status page incident with services and incident updates.
`create-status-page-incident`	Write	Create a new status page incident and optionally notify subscribers. Not idempotent.
`update-status-page-incident`	Write	Post a progress update to an existing incident and optionally notify subscribers. Not idempotent.
`resolve-status-page-incident`	Write	Resolve an incident by posting a final resolved update and optionally notifying subscribers. Not idempotent.

Example prompts:

Prompt

Show open status page incidents and summarize their latest updates.

Prompt

Draft a major status page incident for the API outage and wait for confirmation before notifying subscribers.

Usage tools

Tool	Type	Description
`get-usage-terms`	Read	List organization usage terms with dates, budgets, pricing rules, and covered accounts. Supports date filters and cursor pagination. Use returned term IDs in summary and series filters or projection requests.
`get-usage-summary`	Read	Return credits, pricing-rule breakdowns, and coverage gaps across usage terms. Optionally request a whole-term forecast with `projection: { usageTermsId, asOf? }`.
`list-usage-series`	Read	Return cursor-paginated v2 usage for `day`, `week`, `month`, or `total` intervals. Optionally group by account, usage term, pricing rule, and check type. Include calculations, physical run counts, or observed monitor days.

Usage tools use the v2 Usage API and report on the whole organization the selected account belongs to. They require the usage:read account permission, which Owner and Admin have by default. Use usageTermsIds, accountIds, and pricingRuleKeys arrays to narrow summary or series. V2 has no checkTypes filter. Series defaults to ungrouped daily buckets; pass groupBy and include as arrays. get-usage-terms returns a data collection and nextId, including future terms when you omit dates. Summary returns totals.creditsUsed, breakdown, and coverage, rather than v1 meters. To include a forecast, supply one term ID in projection.usageTermsId. Its optional asOf defaults to yesterday UTC. The forecast covers the term’s whole account scope and budget, independently of the report filters. The optional projection result contains either data or error, so an unavailable forecast does not discard a successful summary. Example prompt:

Prompt

Show my organization's credit usage this month, broken down by check type, and how it projects against the budget.

Getting Started

Detect

Communicate

Resolve

AI

Integrations

Account tools

Check tools

List and filter checks

Create, update, and delete checks

Interactive view tools

Check group tools

Alert channel tools

Test session tools

Result asset tools

Root cause analysis tools

Environment variable tools

Status page tools

Incident tools

Usage tools

​Account tools

​Check tools

​List and filter checks

​Create, update, and delete checks

​Interactive view tools

​Check group tools

​Alert channel tools

​Test session tools

​Result asset tools

​Root cause analysis tools

​Environment variable tools

​Status page tools

​Incident tools

​Usage tools

Account tools

Check tools

List and filter checks

Create, update, and delete checks

Interactive view tools

Check group tools

Alert channel tools

Test session tools

Result asset tools

Root cause analysis tools

Environment variable tools

Status page tools

Incident tools

Usage tools