About OpsKitty
OpsKitty is a hosted MCP server for monitoring websites and APIs, managing status pages and cron heartbeats, and running Lighthouse and SEO audits. It is aimed at people using AI apps to configure and inspect these operations through MCP tools rather than a dashboard.
Key features
- 01Monitor websites and API endpoints
- 02Configure alerts and integrations
- 03Create status pages and incident updates
- 04Manage cron job heartbeats
- 05Run Lighthouse and SEO audits
- 06Submit URLs for indexing and check status
Use cases
- 01Set up uptime checks for a site and health endpoint
- 02Create a public status page for API components
- 03Track a scheduled backup with a heartbeat URL
- 04Audit a page's performance or SEO
MCP support
Provides about 100 tools through a hosted streamable HTTP MCP server at `https://mcp.opskitty.com/mcp`, with OAuth authentication. MCP clients connect to the service; changes and deletions are marked to prompt for confirmation.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.opskitty.com/mcpclaude mcp add --transport http com-opskitty https://mcp.opskitty.com/mcp{"mcpServers":{"com-opskitty":{"type":"http","url":"https://mcp.opskitty.com/mcp"}}}Open in Cursor{"servers":{"com-opskitty":{"type":"http","url":"https://mcp.opskitty.com/mcp"}}}Open in VS Code{"mcpServers":{"com-opskitty":{"type":"http","url":"https://mcp.opskitty.com/mcp"}}}{"mcpServers":{"com-opskitty":{"serverUrl":"https://mcp.opskitty.com/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
Details
From the project README
OpsKitty MCP
Uptime checks for sites and APIs, status pages, cron heartbeats, Lighthouse and SEO audits, run from your AI app.
Website · Docs · Pricing · MCP Registry
OpsKitty is a hosted MCP server at https://mcp.opskitty.com/mcp. Connect it to Claude, ChatGPT, Cursor or any MCP client and set up monitoring by asking for it, instead of clicking through a dashboard.
This repo holds the install files for Claude Code, Codex, Cursor and other clients. The server itself is hosted by OpsKitty, so there is nothing to run.
What you can ask
- "Monitor https://example.com and its /api/health endpoint every minute, and alert me on Slack if either goes down."
- "Create a public status page for my API with the checkout and login endpoints on it."
- "Set up a heartbeat for my nightly backup job and tell me the URL to ping."
- "Run Lighthouse on my homepage and list the three fixes that would help most."
- "Audit the SEO of my pricing page and submit the new blog URLs for indexing."
Install
Claude Code
claude plugin marketplace add capaxelabs/plugins
claude plugin install opskitty@capaxe
Then run /mcp in Claude Code, pick opskitty and sign in to OpsKitty.
Prefer a plain MCP server over a plugin:
claude mcp add --transport http opskitty https://mcp.opskitty.com/mcp
Claude.ai and Claude Desktop
- Open Settings > Connectors and select Add custom connector.
- Name it OpsKitty and paste
https://mcp.opskitty.com/mcp. - Select Connect and sign in.
ChatGPT
- Open Settings > Apps & Connectors > Advanced settings and turn on Developer mode.
- In Apps & Connectors, select Create.
- Name it OpsKitty, paste
https://mcp.opskitty.com/mcpand choose OAuth.
Codex
codex plugin marketplace add capaxelabs/plugins
codex plugin add opskitty@capaxe
Or add it as a plain MCP server:
codex mcp add opskitty --url https://mcp.opskitty.com/mcp
Cursor
Use the Add to Cursor button above, or add to ~/.cursor/mcp.json:
{
"mcpServers": {
"opskitty": { "url": "https://mcp.opskitty.com/mcp" }
}
}
VS Code
Use the Install button above, or add to .vscode/mcp.json:
{
"servers": {
"opskitty": { "type": "http", "url": "https://mcp.opskitty.com/mcp" }
}
}
Any other MCP client
| Setting | Value |
|---|---|
| URL | https://mcp.opskitty.com/mcp |
| Transport | Streamable HTTP |
| Auth | OAuth |
Tools
About 100 tools, grouped by what they cover:
| Area | Examples |
|---|---|
| Websites and endpoints | create_website, create_endpoint, test_endpoint, get_endpoint_monitoring, get_monitoring_stats |
| Alerts and integrations | create_alert, create_integration, test_integration, list_alert_events |
| Status pages and incidents | create_status_page, create_status_component, create_status_incident, post_status_incident_update |
| Cron heartbeats | create_heartbeat, get_heartbeat, rotate_heartbeat_url |
| Performance and SEO | run_lighthouse, run_seo_check, run_site_seo_audit, audit_page_seo |
| Search indexing and AI visibility | submit_urls_for_indexing, check_index_status, run_ai_visibility_test |
| Team and billing | list_organizations, invite_member, get_billing, list_plans |
Tools that change or delete things are marked as such, so your AI app asks before it runs them.
Links
- Website: https://www.opskitty.com
- Docs: https://www.opskitty.com/docs
- Pricing: https://www.opskitty.com/pricing
- Privacy: https://www.opskitty.com/pages/privacy
- Terms: https://www.opskitty.com/pages/tos
- Support: https://www.opskitty.com/contact
Files in this repo
| File | Read by |
|---|---|
.claude-plugin/plugin.json, .mcp.json | Claude Code |
plugin.json, mcp.json | Codex and other Agent Plugins clients |
.cursor-plugin/plugin.json | Cursor |
server.json | Official MCP Registry |
glama.json | Glama |
License
The files in this repo are MIT licensed. Use of the OpsKitty service is covered by its terms.
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.