Skip to main content
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 OAuth permission. Some write tools also require a matching Checkly account role, such as Admin or Read & Write.

​
Account tools

ToolTypeDescription
whoamiReadReturn the authenticated user and account memberships visible to the MCP session.
get-account-entitlementsReadReturn the resolved account plan and feature entitlement state.
list-account-membersReadList account members and pending invites.
invite-account-memberWriteInvite a user to the resolved account. Requires Owner or Admin access, sends an invite email, and is not idempotent.
prepare-local-check-authoringReadReturn 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

ToolTypeDescription
get-check-statusReadReturn a paginated, filterable list of current check status rows, including check type, activation state, and passing, degraded, or failing state.
list-check-resultsReadList 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-resultReadReturn compact detail for one check result.
get-check-performance-summaryReadReturn average, P50, P95, and P99 response-time metrics for one check over a date range when data is available.
trigger-checksWriteRun existing deployed checks on demand and record the run as a test session. Consumes check-run execution quota.
For large accounts, start with get-check-status filters instead of asking for every check at once. 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.
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. trigger-checks only runs checks that already exist on the account. Use prepare-local-check-authoring and the Checkly CLI when you need to create, test, or deploy local check code. Example prompts:
Prompt
Show me the first page of failing API checks tagged production, then summarize what changed in their latest results.
Prompt
Trigger the checks tagged production-smoke, then poll the test session until results are available.

​
Test session tools

ToolTypeDescription
list-test-sessionsReadList recent test sessions with filters and cursor ordering.
get-test-sessionReadReturn one test session and compact result rows.
get-test-session-resultReadReturn 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

ToolTypeDescription
list-check-result-assetsReadReturn a normalized asset manifest for a check result.
fetch-check-result-assetReadFetch 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-assetsReadReturn a normalized asset manifest for a test-session result.
fetch-test-session-result-assetReadFetch 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

ToolTypeDescription
get-error-group-root-cause-analysesReadReturn a check or test-session error group and any existing root cause analyses.
get-root-cause-analysisReadReturn one root cause analysis by RCA ID. Pending analyses return compact polling status.
trigger-root-cause-analysisWriteTrigger 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

ToolTypeDescription
list-account-environment-variablesReadList account-level variables and secrets. Secret values are returned as null.
get-account-environment-variableReadGet one account-level variable by key. Secret values are returned as null.
create-account-environment-variableWriteCreate an account-level variable or secret. Secret values are encrypted and not echoed back.
update-account-environment-variableWriteUpdate 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

ToolTypeDescription
list-status-pagesReadList status pages, including cards and services needed for incident targeting.
get-status-pageReadGet one status page with cards and services.
Example prompt:
Prompt
List my status pages and show the service IDs for the production page.

​
Incident tools

ToolTypeDescription
list-status-page-incidentsReadList status page incidents, optionally filtered by page and incident status.
get-status-page-incidentReadGet one status page incident with services and incident updates.
create-status-page-incidentWriteCreate a new status page incident and optionally notify subscribers. Not idempotent.
update-status-page-incidentWritePost a progress update to an existing incident and optionally notify subscribers. Not idempotent.
resolve-status-page-incidentWriteResolve 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.