openstatus logoDocsPricingDashboard

Manage your status page from Claude, ChatGPT or Cursor

Connect Claude, ChatGPT, Cursor, and any other Model Context Protocol client to your workspace — sign in with OAuth, pick a workspace, and get audit-logged mutations with explicit notify semantics.

The openstatus MCP server connects Claude Desktop, ChatGPT, Cursor, and any other Model Context Protocol client to your workspace — so an AI assistant can read monitors, response logs, and audit history, and drive status pages, status reports, and maintenance windows directly from a conversation.

Quickstart

https://api.openstatus.dev/mcp

Add the URL as a custom connector in Claude, ChatGPT, or Cursor, or run claude mcp add --transport http openstatus https://api.openstatus.dev/mcp for Claude Code. The client opens a consent screen, you pick a workspace and an access level, and the openstatus tools appear in the picker. The server is stateless Streamable HTTP and scales horizontally.

What you can do

The server exposes 46 workspace tools plus four public content tools, grouped by entity:

  • Status pages — list_status_pages · list_page_components · create_status_page · update_status_page · add_page_component · update_page_component · create_component_group · update_component_group
  • Status reports — list_status_reports · get_status_report · create_status_report · add_status_report_update · update_status_report · resolve_status_report · update_status_report_update · delete_status_report_update
  • Maintenance — list_maintenances · get_maintenance · create_maintenance · update_maintenance · add_maintenance_update · update_maintenance_update · delete_maintenance_update
  • Incidents — list_incidents · get_incident · declare_incident · update_incident · set_incident_status · resolve_incident · add_incident_note · get_postmortem · draft_postmortem · approve_postmortem
  • Monitors — list_monitors · get_monitor · get_monitor_status · get_monitor_summary · create_monitor · update_monitor
  • Response logs — list_response_logs · get_response_log
  • Notifications — list_notifications
  • Private locations — list_private_locations
  • Workspace — get_workspace
  • Audit log (workspaces on the audit-log plan only) — list_audit_logs · get_audit_log
  • Content (public openstatus.dev pages) — search_docs · get_doc_page · search_content · get_content_page

The four publishing tools (create_status_report, add_status_report_update, resolve_status_report, create_maintenance) require notify: true | false — the assistant must explicitly choose whether to notify subscribers, so an LLM cannot quietly fan out an alert. update_status_report is metadata-only and cannot notify.

The update tools take an id plus only the fields that change. The assistant reads the current object first (get_monitor, get_maintenance, list_page_components) and leaves everything it does not send untouched; update_monitor is also how it pauses a monitor or links a notification channel. There are no delete tools for monitors, pages, components or groups, and a page's custom domain, access control and theme stay in the dashboard.

The same tool registry powers the in-app assistant — every tool you see in /chat is the same tool you call over MCP, kept in sync by shape-equivalence tests.

Auth & scopes

The MCP server is an OAuth 2.1 authorization server. Connect from any client that implements the MCP authorization spec and you get a consent screen instead of a key to paste: pick the workspace and an access level: Read only, Read & write, or a custom set per resource. Tokens rotate automatically, and every connection is listed under Settings > Integrations > Connected apps, where it can be revoked with immediate effect.

For CI and headless agents, the x-openstatus-key header still works — the same API key the CLI, API, and Terraform use, from Settings > General > API Keys.

Both credentials carry scopes per resource: monitors, pages, incidents, notifications and subscribers, each read or write, with Read only, Read & write and Custom on the consent screen. A connection never sees tools its scopes can't call in tools/list — they don't exist for that session. Write tools throw a clean error if a credential somehow attempts them anyway.

Every mutation lands in the audit log under actor_type = 'mcp', so you can trace any change back to a connection, a user, and a transport.

Other surfaces

  • Want chat inside the dashboard instead of an external client? See the in-app assistant.
  • Want a terminal interface for AI agents (Claude Code, etc.)? See skills on the CLI page.
  • Building an in-app integration? Call the API directly.
  • Want Slack instead of Claude or ChatGPT? See the Slack agent.

Setup guides

Reference

Full tool schema, error codes, and per-client config in the MCP reference.

Frequently asked questions

What does the MCP server let an assistant do?

The MCP server exposes 46 tools scoped to your workspace: list status pages, monitors, response logs, notifications, private locations, and audit logs; inspect a single monitor, maintenance window or response log; create and update monitors (including pausing one and linking notification channels), status pages, page components and component groups; create, update, and resolve status reports; schedule and reschedule maintenance windows; declare incidents, change their status, add timeline notes, and draft and approve the postmortem. There are no delete tools for monitors, pages, components or groups. Every mutation writes to the audit log, and publishing tools require an explicit notify decision.

Are skills different from the MCP server?

Skills are prompt and command bundles installed into your local agent (Claude Code, etc.) that wrap the openstatus CLI. The MCP server is a remote endpoint that any MCP-compatible client can connect to. Skills are great for terminal-shaped workflows; MCP is great for chat-shaped workflows.

Do I need an API key to connect an MCP client?

No. The MCP server is an OAuth 2.1 authorization server: Claude, ChatGPT, Cursor, and other clients open a consent screen where you pick a workspace and an access level (Read only, Read & write, or a custom set per resource), and tokens are issued and refreshed automatically. The x-openstatus-key header still works for CI and headless agents, with the same key the CLI, API, and Terraform use.

Can the assistant accidentally notify subscribers?

No. Every publishing tool requires the assistant to set notify: true | false explicitly — there's no default. Metadata-only edits like update_status_report can't notify at all. Every mutation lands in the audit log under actor_type = 'mcp', so you can see exactly what happened.