Using the MCP server

Undownable has a first-party MCP server, so AI agents like Claude can run your monitoring for you: create monitors, check what's up and what's down, review incidents, and publish status pages. Everything an agent does is scoped to your team and governed by the same permissions as the dashboard.

Server address

https://undownable.com/mcp

Streamable HTTP transport, authenticated with an Authorization: Bearer <token> header.

1. Create an API token

Log in and open API tokens in the dashboard sidebar.
Name the token after the agent that will use it (for example claude-code) and create it.
Copy the token immediately: it is shown exactly once.

Tokens act as you, on your current team. Revoke one from the same page at any time and the agent loses access instantly.

2. Add the server to your client

Claude Code

One command in your terminal:

claude mcp add --transport http undownable https://undownable.com/mcp \
  --header "Authorization: Bearer YOUR_TOKEN"

Claude Desktop

Add this to the mcpServers section of your claude_desktop_config.json (Settings, Developer, Edit Config):

"undownable": {
  "command": "npx",
  "args": [
    "mcp-remote", "https://undownable.com/mcp",
    "--header", "Authorization: Bearer YOUR_TOKEN"
  ]
}

Any other MCP client

Point it at https://undownable.com/mcp using the HTTP (streamable) transport and send Authorization: Bearer YOUR_TOKEN with every request. Most clients accept a config shaped like:

{
  "url": "https://undownable.com/mcp",
  "headers": { "Authorization": "Bearer YOUR_TOKEN" }
}

3. Ask your agent

That's the whole setup. Your agent discovers the tools on its own; you just talk to it:

"Monitor https://example.com every 5 minutes and alert me if it goes down."
"Is anything down right now? Show me this week's incidents."
"Add an SSL check for example.com and a TCP check for db.example.com:5432."
"Create a heartbeat monitor for my nightly backup job and give me the ping URL."
"Set up a public status page with my production monitors on it."
"Pause the staging monitors while we deploy, then resume them."

What agents can do

Tool	What it does
`list-monitors`	Every monitor with its current status, check interval, and ID
`create-monitor`	Create HTTP, keyword, SSL, TCP, DNS, ping, or heartbeat monitors; checks start within a minute
`get-monitor`	One monitor in detail: 24h, 7d, and 30d uptime plus recent incidents
`pause-monitor` / `resume-monitor`	Silence checks and alerts during maintenance, then bring them back
`delete-monitor`	Remove a monitor and stop collecting its history
`list-incidents`	Recent outages across the team, filterable to one monitor or only ongoing ones
`list-status-pages`	Your status pages with their public URLs and overall status
`create-status-page`	Publish a public status page with chosen monitors, in display order

Good to know

Scoped to your team

A token only ever sees the team it belongs to, and destructive actions respect your team role.

Plan limits apply

Monitor count, fastest check interval, and status page count follow your plan. When a limit is hit, the agent gets a clear message saying so.

Rate limited

60 requests per minute per token, plenty for interactive agent sessions.

Revoke any time

Revoking a token on the API tokens page cuts the agent off immediately. Nothing else about your account changes.

Give your agent a job

Free includes 10 monitors, every alert channel, and a public status page. No card required.

Start monitoring free