uptybots-mcp-server
Uptime monitoring for websites, APIs, SSL certificates, domain expiry, ping and TCP/UDP ports. 15 tools to list, create, pause and delete monitors, pull incident timelines with error codes, and read hourly or daily uptime and response-time statistics.
README
UptyBots MCP Server
Connect AI assistants like Claude, Cursor, and other MCP-compatible tools to your UptyBots uptime monitors.
What is this?
An MCP (Model Context Protocol) server that gives AI assistants access to your UptyBots monitoring data. Ask your AI to check monitor status, review incidents, create new monitors, and more — through natural conversation.
You probably want the hosted server instead
There is now a remote server that needs no install and no API key:
https://mcp.uptybots.com/mcp
Add that URL to your client and it opens a browser for you to sign in and approve access. If you do not have an UptyBots account yet, you can create one at that step.
With Claude Code:
claude mcp add --transport http uptybots https://mcp.uptybots.com/mcp
then run /mcp, pick uptybots and authenticate.
This package is the local alternative. It runs on your own machine and authenticates with an API key instead of a browser sign-in — the right choice for MCP clients that cannot talk to remote servers, and for offline or self-contained setups. It exposes the same 15 tools and is not going away.
Prerequisites
- Node.js 18 or later
- A UptyBots account
- An API key from Account → API Keys
Setup
1. Configure your AI client
No install step needed: npx fetches the published package on first run.
Add to your MCP client configuration:
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"uptybots": {
"command": "npx",
"args": ["-y", "uptybots-mcp-server"],
"env": {
"UPTYBOTS_API_URL": "https://uptybots.com",
"UPTYBOTS_API_KEY": "upty_your_api_key_here"
}
}
}
}
Claude Code (~/.claude/settings.json) and Cursor (.cursor/mcp.json) use the same format.
2. Restart your AI client
The MCP tools will be available immediately.
Running from source (optional)
To run a local checkout instead of the npm package:
git clone https://github.com/uptybots/mcp-server.git
cd mcp-server
npm install
Then point the client at the checkout:
{
"mcpServers": {
"uptybots": {
"command": "node",
"args": ["/path/to/mcp-server/index.js"],
"env": {
"UPTYBOTS_API_URL": "https://uptybots.com",
"UPTYBOTS_API_KEY": "upty_your_api_key_here"
}
}
}
}
Available Tools (15)
Read
| Tool | Description |
|---|---|
list_monitors |
List all monitors with filters (type, status) |
get_monitor |
Get monitor details by ID |
get_incidents |
Get downtime incidents for a monitor |
get_stats_hourly |
Hourly performance stats |
get_stats_daily |
Daily performance stats |
get_notifications |
Notification history |
Create
| Tool | Description |
|---|---|
create_http_monitor |
Create HTTP/HTTPS monitor |
create_api_monitor |
Create API endpoint monitor |
create_ping_monitor |
Create ICMP ping monitor |
create_port_monitor |
Create TCP port monitor |
create_ssl_monitor |
Create SSL certificate monitor |
create_domain_monitor |
Create domain expiration monitor |
Manage
| Tool | Description |
|---|---|
pause_monitor |
Pause a monitor |
resume_monitor |
Resume a paused monitor |
delete_monitor |
Delete a monitor |
Environment Variables
| Variable | Required | Description |
|---|---|---|
UPTYBOTS_API_URL |
No | API base URL (default: https://uptybots.com) |
UPTYBOTS_API_KEY |
Yes | Your API key (starts with upty_) |
Documentation
- MCP Server Docs — full setup guide and tool reference, covering both the hosted server and this one
- REST API Reference — the API that powers the MCP server
- Account → Connected Applications — review and revoke access granted through the hosted server
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.