MCP App Store
by KeenEthics
Stackpulse icon

Stackpulse MCP Server for Claude

By Stackpulse

Overview

Stackpulse puts the services your product depends on (out of 9,700+ official status pages: AWS, Cloudflare, Stripe, Twilio, GitHub…) on one dashboard with your own websites and API endpoints, checked every minute. This connector gives Claude that dashboard and its history, so it can answer the questions a single status page can't. Things to ask: - "Is anything on my stack down right now?" Every vendor and URL on your dashboards, problems first. - "Our API got slow around 3 pm. Is it us or one of our vendors?" Your URL monitor's checks beside your vendors' problems from that time. - "What went wrong on our stack this week?" Every incident across your vendors and URLs, with what else broke at the same time. - "Which of our vendors was least reliable this quarter?" Time with problems by severity, incidents and recovery for each, and which vendors tend to break together. - "How has our checkout endpoint done this month?" Uptime, response times, failed checks and its certificate. - "Add Twilio and Postmark to our Production dashboard and watch api.example.com." With Read & write access it can also create and rename dashboards, add or remove services, add URL monitors, run a check now, and pause or resume one. The only removal is taking services off a dashboard. Any of the 9,700+ services can be looked up too, dashboard or not. You need a Stackpulse account on Pro ($39 a month; every new account gets a 14-day trial, no card). You sign in with Stackpulse, the connection starts read-only and asks again before it may change anything, and you can limit it to some dashboards. Disconnect any time in Settings → API & MCP.

How to connect

  1. Claude: Open the Stackpulse listing in the Claude connectors directory and choose Connect. Claude listing Stackpulse exposes 16 tools here.

Tools

add_monitor

Claude
Watches a website or API endpoint on a dashboard: checks the address once first, and refuses what the app refuses (private addresses, other ports, past the plan). Without a name, the page’s title names it. Headers and request bodies stay in the app.

add_services

Claude
Adds services to a dashboard by slug (search_services finds them), within the plan’s limit.

check_monitor

Claude
Checks one of the account’s URL monitors now, as Check now does in the app, and says what it got.

create_dashboard

Claude
Makes a dashboard with a name and, optionally, services by slug (search_services finds them), within the plan’s dashboards and services. Answers with its address.

get_incident_history

Claude
Incidents on a dashboard in a window: the ones that started in it (with what else started at the same time) and the ones already going on. As far back as the plan’s history goes.

get_monitor

Claude
One of the account’s URL monitors: its status, its uptime over the last 30 days (or since it started) with the failed checks apart, response times, its certificate and its latest checks.

get_reliability

Claude
How reliable a dashboard’s services and URL monitors were over 7, 30 or 90 days: the least reliable first, with the share of time without a reported problem (minor issues count, so one long minor issue makes it low), time in each severity, incidents and recovery, and what tends to break together.

get_service

Claude
One service’s status from its official status page: what’s wrong, the components with a problem, 90 days of history and recent incidents.

get_stack_status

Claude
What’s going on now on a dashboard: a summary, then every service and URL monitor with a problem, with when the problem began and when its current status did. A URL monitor that’s down lists what started around then. Without a dashboard, every dashboard.

list_dashboards

Claude
The account’s dashboards (the ones this connection can see), with how many services and URL monitors each has and its worst status now.

list_outages

Claude
Services reporting a problem right now, the newest first: the 25 best-known, unless all is true or a limit is given.

pause_monitor

Claude
Pauses a URL monitor, e.g. during a deploy: an open incident ends, and no alerts go out until it’s resumed.

remove_services

Claude
Takes services off a dashboard. Their history stays; adding one back shows it again.

rename_dashboard

Claude
Renames a dashboard. Its status page shares the name.

resume_monitor

Claude
Resumes a paused URL monitor: it’s checked at once and starts fresh.

search_services

Claude
Finds services in the catalog of 9,700+ status pages by name, with their status now. Use it to find a service’s slug.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/stackpulse"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/stackpulse)