MCP.Market

Alertchecker MCP server

online · 100% uptime
by steve-chambers·io.github.steve-chambers/alertchecker-mcp·v1.0.0
No reviews yet

Create AI-monitored web alerts from plain English — just say "Alert me when..."

A97/100grade A
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
A97/100

full report

Adoption
Growing

0 stars

Reviews

Write one

Nobody has reviewed Alertchecker yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Alertchecker tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Public scan report

scanner v0.1.9 · 2026-09-23 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 524ms (auth required)20/20
  • –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
  • Auth qualityOAuth resource metadata advertised on 40115/15
  • Maintenancelast push 2 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 97/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Alertchecker compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
97/100
higher than 98% of 48,255 servers
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
67 ms
faster than 90% of 30,031 servers

Install Alertchecker in Claude Code, Cursor or VS Code

claude mcp add --transport http alertchecker-mcp https://alertchecker.com/api/mcp
Add to Cursor

What the publisher says

From the Alertchecker repository's README, as published. We do not edit it. Read it on GitHub

AlertChecker MCP Server

Gives any MCP-compatible AI assistant (ChatGPT, Claude, and others) the ability to create AI-monitored web alerts on your behalf. Then you will be told when something happens instead of having to ask — just say "Alert me when..."

What it does

AlertChecker watches the web for you and emails you when a plain-English statement becomes true. Once you connect this MCP server, any supporting AI assistant can create these alerts directly from natural conversation.

Example prompts:

  • "Alert me when the iPhone 16 Pro is back in stock at apple.com"
  • "Let me know whenever it's going to rain in London tomorrow"
  • "Email me when Tesla stock drops below $200"
  • "Tell me if there's an earthquake over 4.0 magnitude in California"

Tools

Icon

A public icon suitable for connector setup is available at alertchecker.com/app-icon.png — PNG, 256x269px, under 9KB.

Connecting

Server URL: https://alertchecker.com/api/mcp

Transport: Streamable HTTP

Authentication: OAuth 2.0 with PKCE and Dynamic Client Registration (RFC 7591). No manual API key or client credentials needed — your MCP client discovers everything automatically from:

https://alertchecker.com/.well-known/oauth-authorization-server

On first connection, you'll be redirected to sign in via Google or a magic email link.

Adding to ChatGPT

  1. Go to Settings → Plugins → Browse plugins
  2. Click the New Plugin button (plus icon, top-right)
  3. Fill in:
  • Icon (optional): upload alertchecker.com/app-icon.png — otherwise a generic icon is shown
  • Name: AlertChecker
  • Description: Create AI-monitored web alerts from plain English
  • Connection ("Server URL" option selected): https://alertchecker.com/api/mcp
  • Authentication: OAuth
  1. Tick the checkbox confirming you understand the risks
  2. Click Create, then click Sign in with AlertChecker — you'll be redirected to sign in via Google or magic link
  3. In a new chat, enable AlertChecker from the "Add files and more" button (plus icon, just to the left of where you type your chat). Then ask: "Alert me when..."

Adding to Claude

  1. Go to Settings → Customize → Connectors → Add → Add custom connector
  2. Fill in:
  • Name: AlertChecker
  • Remote MCP server URL: https://alertchecker.com/api/mcp
  1. Click Add
  2. Click Connect
  3. Sign in
  4. Optionally change Needs approval to Always allow for the Create alert tool
  5. In a new chat, enable AlertChecker from the Connectors submenu under the "Add files, connectors and more" button (plus icon, just to the left of where you type your chat). Then ask: "Alert me when..."

Adding to Perplexity

  1. Go to All settings → Connectors → Add custom connector (top-right)
  2. Click Change icon and upload alertchecker.com/app-icon.png
  3. Fill in:
  • Name: AlertChecker
  • Description (optional): Create AI-monitored web alerts from plain English
  • MCP Server URL: https://alertchecker.com/api/mcp
  1. Tick the checkbox confirming you understand the risks
  2. Sign in when prompted
  3. In a new chat, enable AlertChecker from the "Add files or tools" button (plus icon, just to the left of where you type your chat). Then ask: "Alert me when..."

Learn more

  • AlertChecker — the main app
  • Model Context Protocol — the open standard this server implements

Support

Questions or issues: support@alertchecker.com

Nothing above is checked by us. What we check is on the safety report.

Alertchecker: common questions

Is Alertchecker MCP server safe?
Yes, by our scan: it is graded A (97/100). Read the Alertchecker safety report
How do I install Alertchecker?
It runs remotely at alertchecker.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Alertchecker need an API key?
No key to paste: it signs you in with OAuth when your client connects.
Is Alertchecker maintained?
The last commit was 44 days ago (2026-09-21). The latest release is v1.0.0.
Is Alertchecker up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Alertchecker compare with other MCP servers?
safety score 97/100 (higher than 98% of 48,255 servers); uptime 100% (of our recent checks; the typical remote server answers 100%); response time 67 ms (faster than 90% of 30,031 servers). Full comparison.