Model Context Protocol (MCP) Integration

Model Context Protocol (MCP) Integration

UpMonitor supports the Model Context Protocol (MCP), allowing AI agents (Claude Desktop, Claude Code, Cursor, and any MCP-compatible client) to directly perform website diagnostics and monitoring tasks.

**New: Active Incident handoff.** When a monitor degrades, the [Active Incident panel](/docs/active-incident) generates a copy-pasteable prompt that drops the entire incident context - root cause, remediation steps, deep link - into your AI agent in one click. The MCP server is what turns that prompt into structured, queryable context. See the [agentic setup guide](/docs/agentic-setup) for the per-tool install path.

Why use MCP with UpMonitor?

By connecting UpMonitor to your AI agent, you can ask questions like:

  • "Is my website's SSL certificate valid?"
  • "Check if https://mysite.com has security headers configured."
  • "What's my current API usage this month?"

The agent calls the right tool, summarizes the output, and suggests fixes - all without leaving your IDE.

Configuration

Claude Desktop

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "upmonitor": {
      "command": "npx",
      "args": ["-y", "@upmonitor/mcp-server"],
      "env": {
        "UPMONITOR_API_KEY": "up_..."
      }
    }
  }
}

Claude Code

claude mcp add upmonitor \
  -e UPMONITOR_API_KEY=up_... \
  -- npx -y @upmonitor/mcp-server

Cursor

Add to Settings → MCP → Add Server:

{
  "upmonitor": {
    "command": "npx",
    "args": ["-y", "@upmonitor/mcp-server"],
    "env": {
      "UPMONITOR_API_KEY": "up_..."
    }
  }
}

Available Tools

Once connected, your AI agent has access to the following tools:

`run_audit`

Runs a full diagnostic check on a URL (SSL, DNS, HTTP, performance, security headers).

  • Arguments:
    • url (string, required) - the URL to audit, e.g. https://example.com
    • checkers (string[], optional) - subset of checkers, e.g. ["ssl", "dns"]
  • Returns: full JSON report including individual checker results, overall status, and latency.

`get_usage`

Returns current API usage and quota status for your API key.

  • Arguments: none
  • Returns: remaining requests, rate limit, quota window, tier info.

Coming soon

The following tools are landing in the next release:

  • get_active_incident(monitor_id) - returns the structured Active Incident object (root cause, remediation, estimated impact) so the agent can reason over the diagnosis without parsing the prompt text.
  • get_monitor_status(monitor_id) - recent history and current state for a continuous monitor
  • add_monitor(url, interval) - create a new continuous monitor from the agent

For now, manage continuous monitors at upmonitor.io/dashboard.

Security

The MCP integration uses your standard UpMonitor API key. Treat it like a password:

  • Never commit it to a public repository.
  • Rotate it via Developer Settings → API Keys, if exposed.
  • Use the UPMONITOR_API_KEY environment variable, not config file paths checked into git.