mcpField
U
uptrack-mcp

uptrack-mcp

Remote
uptrack.appCloud & Infra0Updated 4d ago

About uptrack-mcp

uptrack-mcp connects AI clients to Uptrack uptime monitoring. It supports remote MCP with OAuth and stdio for managing monitors and incidents.

Key features

  1. 01List and inspect monitors
  2. 02Create and configure monitors
  3. 03Pause, resume, and delete monitors
  4. 04List and retrieve incidents
  5. 05Acknowledge open incidents
  6. 06Remote OAuth and stdio transports

Use cases

  1. 01Review monitor status and uptime
  2. 02Set up HTTP, TCP, DNS, SSL, or heartbeat checks
  3. 03Investigate recent service incidents
  4. 04Acknowledge an open incident

MCP support

The server exposes Uptrack monitor and incident operations as MCP tools. It supports a remote endpoint using OAuth 2.0 + PKCE and a stdio transport using an API key.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://api.uptrack.app/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

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

@uptrack-app/mcp

MCP server for Uptrack uptime monitoring. Use with Claude.ai, ChatGPT, Cursor, VS Code, Windsurf, or any MCP-compatible AI assistant.

Two transports supported:

  • Remote MCP (recommended) — https://api.uptrack.app/mcp with OAuth 2.0 + PKCE. No API key paste, no npm install. Works in Claude.ai, ChatGPT, VS Code (1.100+), Cursor, and Windsurf.
  • Stdio (this package) — for offline agents, CI runners, Claude Desktop, and any client that can't reach a remote MCP endpoint.

Remote MCP (OAuth)

The fastest path. Use this if your client supports remote MCP + OAuth.

ClientInstall
CursorAdd a remote MCP server → paste https://api.uptrack.app/mcp
VS Code 1.100+Add a remote MCP server → paste https://api.uptrack.app/mcp
WindsurfAdd a remote MCP server → paste https://api.uptrack.app/mcp
Claude.aiSettings → Connectors → Add custom connector → paste https://api.uptrack.app/mcp
ChatGPTSettings → Connectors → Add remote MCP → paste https://api.uptrack.app/mcp

OAuth handles consent in-app. No API key. You need an Uptrack account on a paid plan.

See the Uptrack MCP guide for the full install steps.

Stdio (this package)

Use this when remote MCP isn't available — offline, CI, or Claude Desktop.

Claude Code
claude mcp add uptrack -- env UPTRACK_API_KEY=your_key npx -y @uptrack-app/mcp
Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "uptrack": {
      "command": "npx",
      "args": ["-y", "@uptrack-app/mcp"],
      "env": {
        "UPTRACK_API_KEY": "uk_live_..."
      }
    }
  }
}
Cursor / Windsurf

Add to the MCP settings with the same stdio config as Claude Desktop.

Available Tools

ToolDescription
list_monitorsList all monitors with status, URL, interval, uptime
get_monitorGet details for a specific monitor
create_monitorCreate a new monitor (HTTP, TCP, DNS, SSL, heartbeat)
update_monitorUpdate monitor config
pause_monitorPause an active monitor
resume_monitorResume a paused monitor
delete_monitorDelete a monitor
list_incidentsList recent incidents
get_incidentFetch one incident
acknowledge_incidentAcknowledge an open incident

Example Usage

Once connected, ask your AI assistant:

  • "List my monitors"
  • "Create a monitor for https://example.com that checks every 30 seconds"
  • "Are any of my services down right now?"
  • "Show me recent incidents"
  • "Acknowledge the incident on the API monitor"

Authentication

  • Remote MCP: OAuth 2.0 — no API key needed, consent handled in-app.
  • Stdio: Create an API key in the dashboard under Settings → API Keys. See how to use an API key. API keys need a paid plan.

Links

License

MIT

Comments

Markdown supported

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.