UptyBots Logo UptyBots
UptyBots Blog
← Prev Next →

Connect AI Assistants to Your Uptime Monitors with MCP

What if you could ask your AI assistant: "Are any of my sites down right now?" and get an instant answer with real data from your monitoring dashboard? What if you could say "create an HTTP monitor for staging.myapp.com with 3-minute checks" and have it actually happen, without leaving your conversation? What if your AI could investigate incidents for you, summarize uptime trends, and suggest improvements based on real data from your services? This is no longer hypothetical. Today, that is exactly what UptyBots delivers through MCP integration.

The shift from "AI as a search engine" to "AI as a tool that takes action on your real systems" is one of the most important changes happening in software right now. Instead of asking AI questions and copying answers into other tools, you can let the AI work directly with your tools — read your monitoring data, create new monitors, pause services during deploys, investigate incidents, and more. UptyBots embraces this shift with full MCP support, letting you connect Claude, Cursor, and other MCP-compatible AI assistants directly to your uptime monitoring infrastructure.

We're releasing the UptyBots MCP Server — an integration that connects AI assistants like Claude, Cursor, and other MCP-compatible tools directly to your uptime monitors.

What is MCP?

The Model Context Protocol (MCP) is an open standard created by Anthropic that lets AI assistants interact with external tools and data sources. Think of it as a universal plug that connects your AI to the services you use every day.

Instead of switching between your monitoring dashboard and AI chat, the AI reads your monitoring data directly and responds with real numbers, real status, and real insights.

What Can You Do?

With the UptyBots MCP server, your AI assistant gets access to 15 monitoring tools:

  • Check status — list all monitors, filter by type (HTTP, Ping, SSL, Port, Domain, API) or status (up, down, paused)
  • View details — get full configuration and current state of any monitor
  • Create monitors — set up new HTTP, Ping, Port, SSL, Domain, or API monitors through conversation
  • Manage monitors — pause, resume, or delete monitors
  • Analyze incidents — review downtime history with timestamps and error messages
  • Check performance — get hourly and daily response time stats
  • Review notifications — see what alerts were sent and through which channels

Setup in 3 Steps

Step 1: Get an API Key

Go to Account → API Keys in your UptyBots dashboard and create a key. The key starts with upty_ and is shown only once — save it somewhere secure.

Step 2: Install the MCP Server

Clone the repository and install dependencies:

git clone https://github.com/uptybots/mcp-server.git
cd mcp-server
npm install

Step 3: Configure Your AI Client

Add the MCP server to your client's config. Here's the Claude Desktop example:

{
  "mcpServers": {
    "uptybots": {
      "command": "node",
      "args": ["/path/to/mcp-server/index.js"],
      "env": {
        "UPTYBOTS_API_URL": "https://uptybots.com",
        "UPTYBOTS_API_KEY": "upty_your_key_here"
      }
    }
  }
}

Restart your AI client, and that's it. You can now talk to your monitors.

Real-World Use Cases

  • Morning check-in — "Give me a summary of all my monitors. Anything down overnight?"
  • Incident investigation — "What happened with my API monitor yesterday between 2pm and 4pm?"
  • Quick setup — "Create an HTTP monitor for staging.myapp.com with 3-minute checks"
  • Maintenance mode — "Pause all my staging monitors while I deploy"
  • Performance review — "Show me the daily response times for my main website this week"
  • On-call triage — "Which monitors had incidents in the last 24 hours? Show me the error messages."

Security

The MCP server runs locally on your machine. Your AI client starts it as a subprocess — no data passes through third-party servers. Authentication uses the same API keys as the REST API, with SHA-256 hashed storage and per-account data isolation.

Get Started

Ready to connect your AI assistant to your monitors? Check out the full MCP documentation for detailed setup instructions, the complete tool reference, and configuration examples for Claude Desktop, Claude Code, and Cursor.

Don't have an API key yet? Read the API docs first, or sign up free to get started.

Why Conversational Monitoring Matters

Traditional monitoring dashboards are designed for browsing, not for asking specific questions. You open the dashboard, scan the list of monitors, look for red indicators, click into details if something looks wrong. This works for routine checks but is inefficient for specific investigations. Conversational monitoring through AI assistants flips this around: you ask the question you actually have, and the AI fetches the specific data needed to answer it.

Examples of questions that are awkward to answer with a dashboard but natural with conversation:

  • "Which of my monitors had downtime in the last 7 days, sorted by total downtime?"
  • "What was the average response time for my main API last week compared to the week before?"
  • "Were there any patterns in my recent incidents — did they happen at the same time of day?"
  • "Summarize the health of my entire infrastructure in one paragraph."
  • "Which monitors are paused that shouldn't be?"
  • "Find any monitors with response times over 2 seconds."

These questions all require analyzing data across multiple monitors and time ranges. A dashboard makes you do this analysis manually. An AI with MCP access can do it in seconds.

MCP vs Traditional API Integration

If you have used REST APIs before, you might wonder why MCP matters. Both let you read and modify monitoring data programmatically. The difference is that MCP is designed for AI-driven interaction:

  • Self-describing tools. MCP exposes available actions with descriptions that AI can understand and use without custom integration code.
  • Natural language interface. Users describe what they want; AI translates to the right tool calls.
  • Local execution. The MCP server runs locally on your machine, so your data and credentials never leave your computer.
  • Standardized. Works with any MCP-compatible AI client without per-client integration.
  • Composable. AI can chain multiple tool calls to accomplish complex tasks.

Frequently Asked Questions

What is MCP exactly?

The Model Context Protocol is an open standard for connecting AI assistants to external tools and data sources. Created by Anthropic, it has been adopted by Claude, Cursor, and other AI clients.

Is my data safe?

Yes. The MCP server runs locally on your machine. Your AI client starts it as a subprocess. No data passes through third-party servers beyond the AI service you are already using.

Which AI clients support MCP?

Claude Desktop, Claude Code, Cursor, and a growing number of other AI tools. The MCP standard is open, so any client can implement it.

Do I need a paid plan to use MCP?

The MCP server itself is free and open source. You need an API key from UptyBots, available with both free and paid accounts.

Can I limit what the AI can do?

API keys can be configured with specific permissions. You can create read-only keys for AI assistants that should only fetch data, not modify it.

Blog Demo Library Tutorials

Ready to get started?

Start Free