Checkly MCP Server
Hosted, remote MCP server that lets an agent inspect Checkly checks, check results and test sessions, fetch result assets, read and trigger Rocky AI root cause analyses, manage account environment variables, and read status pages and manage their incidents.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Descriptor
Candidate descriptor · transport
Tools
whoami— Return the authenticated user and account memberships visible to the MCP session.get-account-entitlements— Return the resolved account plan and feature entitlement state.list-account-members— List account members and pending invites.invite-account-member— Invite a user to the resolved account. OAuth-only, requires Owner or Admin access, sends an invite email, and is explicitly documented as not idempotent.prepare-local-check-authoring— Return an account-aware runbook for creating, testing and deploying check code with the local Checkly CLI.list-check-stats— Paginated, filterable list of checks with pass/fail/degraded status; includeReliability adds availability, response-time percentiles and ICMP latency or packet loss.list-check-results— Recent compact results for one check, including response status and assertion counts.get-check-result— Compact detail for one check result.get-check-performance-summary— Average, P50, P95 and P99 response-time metrics for one check over a date range.trigger-checks— Run existing deployed checks on demand and record the run as a test session. Consumes check-run execution quota.list-test-sessions— List recent test sessions with filters and cursor ordering.get-test-session— Return one test session and compact result rows.list-test-session-results— List compact result rows for one test session with bounded pagination.get-test-session-result— Compact detail for one test-session result.list-check-result-assets— Normalized asset manifest for a check result.fetch-check-result-asset— Fetch one check-result asset; text inline under a byte limit, binary or large assets as a download link.list-test-session-result-assets— Normalized asset manifest for a test-session result.fetch-test-session-result-asset— Fetch one test-session-result asset.get-error-group-root-cause-analyses— Return a check or test-session error group and any existing root cause analyses.get-root-cause-analysis— Return one RCA by ID; pending analyses return compact polling status.trigger-root-cause-analysis— Trigger a new RCA for an error group. Requires run access and consumes RCA invocation quota.list-account-environment-variables— List account-level variables and secrets; secret values return as null.get-account-environment-variable— Get one account-level variable by key; secret values return as null.create-account-environment-variable— Create an account-level variable or secret; secret values are encrypted and never echoed back.update-account-environment-variable— Update an account-level variable or secret by key.list-status-pages— List status pages including the cards and services needed for incident targeting.get-status-page— Get one status page with cards and services.list-status-page-incidents— List status page incidents, optionally filtered by page and status.get-status-page-incident— Get one incident with services and incident updates.create-status-page-incident— Create a new incident and optionally notify subscribers. Not idempotent.update-status-page-incident— Post a progress update to an existing incident and optionally notify subscribers. Not idempotent.resolve-status-page-incident— Resolve an incident by posting a final resolved update and optionally notifying subscribers. Not idempotent.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.