Stackpulse
by stackpulse.app · remote · no sign-in to list tools · v1.0.0 · published by app.stackpulse
8,900+ services' status, and your Stackpulse dashboards and URL monitors. Needs Pro.
16 tools: 1 can delete or cancel things, 7 change things and 8 only read.
Scanned Oct 21, 2026
- Deletes or cancels1Claude Code: deny: see these tools
- Can't be undone0Claude Code: ask
- Changes things7Claude Code: ask: see these tools
- Only reads8Claude Code: allow: see these tools
No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.
claude mcp add --transport http stackpulse https://stackpulse.app/mcpTools
Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.
16 tools
Deletes or cancels 1Claude Code: deny
remove_servicesTakes services off a dashboard.No findings
Why it is in this group
- The name "remove_services" says "remove": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Takes services off a dashboard. Their history stays; adding one back shows it again.
Annotations the server declares
- title: Remove services
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
Changes things 7Claude Code: ask
add_monitorWatches 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).No findings
Why it is in this group
- The name "add_monitor" says "add": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- title: Add a URL monitor
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
add_servicesAdds services to a dashboard by slug (search_services finds them), within the plan’s limit.No findings
Why it is in this group
- The name "add_services" says "add": a word for a change.
Description, as the server wrote it Adds services to a dashboard by slug (search_services finds them), within the plan’s limit.
Annotations the server declares
- title: Add services
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
check_monitorChecks one of the account’s URL monitors now, as Check now does in the app, and says what it got.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Checks one of the account’s URL monitors now, as Check now does in the app, and says what it got.
Annotations the server declares
- title: Check a URL monitor now
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
create_dashboardMakes a dashboard with a name and, optionally, services by slug (search_services finds them), within the plan’s dashboards and services.No findings
Why it is in this group
- The name "create_dashboard" says "create": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- title: Create a dashboard
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
pause_monitorPauses a URL monitor, e.g.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Pauses a URL monitor, e.g. during a deploy: an open incident ends, and no alerts go out until it’s resumed.
Annotations the server declares
- title: Pause a URL monitor
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
rename_dashboardRenames a dashboard.No findings
Why it is in this group
- The name "rename_dashboard" says "rename": a word for a change.
Description, as the server wrote it Renames a dashboard. Its status page shares the name.
Annotations the server declares
- title: Rename a dashboard
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
resume_monitorResumes a paused URL monitor: it’s checked at once and starts fresh.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Resumes a paused URL monitor: it’s checked at once and starts fresh.
Annotations the server declares
- title: Resume a URL monitor
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 8Claude Code: allow
get_incident_historyIncidents 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.No findings
Why it is in this group
- The name "get_incident_history" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Get incident history
- readOnlyHint: true
- openWorldHint: false
get_monitorOne 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 c…No findings
Why it is in this group
- The name "get_monitor" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Get a URL monitor
- readOnlyHint: true
- openWorldHint: false
get_reliabilityHow 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…No findings
Why it is in this group
- The name "get_reliability" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Get reliability
- readOnlyHint: true
- openWorldHint: false
get_serviceOne service’s status from its official status page: what’s wrong, the components with a problem, 90 days of history and recent incidents.No findings
Why it is in this group
- The name "get_service" says "get": a word for reading.
Description, as the server wrote it One service’s status from its official status page: what’s wrong, the components with a problem, 90 days of history and recent incidents.
Annotations the server declares
- title: Get a service
- readOnlyHint: true
- openWorldHint: false
get_stack_statusWhat’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.No findings
Why it is in this group
- The name "get_stack_status" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Get stack status
- readOnlyHint: true
- openWorldHint: false
list_dashboardsThe account’s dashboards (the ones this connection can see), with how many services and URL monitors each has and its worst status now.No findings
Why it is in this group
- The name "list_dashboards" says "list": a word for reading.
Description, as the server wrote it The account’s dashboards (the ones this connection can see), with how many services and URL monitors each has and its worst status now.
Annotations the server declares
- title: List dashboards
- readOnlyHint: true
- openWorldHint: false
list_outagesServices reporting a problem right now, the newest first: the 25 best-known, unless all is true or a limit is given.No findings
Why it is in this group
- The name "list_outages" says "list": a word for reading.
Description, as the server wrote it Services reporting a problem right now, the newest first: the 25 best-known, unless all is true or a limit is given.
Annotations the server declares
- title: List outages
- readOnlyHint: true
- openWorldHint: false
search_servicesFinds services in the catalog of 9,700+ status pages by name, with their status now.No findings
Why it is in this group
- The name "search_services" says "search": a word for reading.
Description, as the server wrote it Finds services in the catalog of 9,700+ status pages by name, with their status now. Use it to find a service’s slug.
Annotations the server declares
- title: Search services
- readOnlyHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http stackpulse https://stackpulse.app/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__stackpulse__search_services",
"mcp__stackpulse__get_service",
"mcp__stackpulse__list_outages",
"mcp__stackpulse__list_dashboards",
"mcp__stackpulse__get_stack_status",
"mcp__stackpulse__get_incident_history",
"mcp__stackpulse__get_monitor",
"mcp__stackpulse__get_reliability"
],
"ask": [
"mcp__stackpulse__create_dashboard",
"mcp__stackpulse__rename_dashboard",
"mcp__stackpulse__add_services",
"mcp__stackpulse__add_monitor",
"mcp__stackpulse__check_monitor",
"mcp__stackpulse__pause_monitor",
"mcp__stackpulse__resume_monitor"
],
"deny": [
"mcp__stackpulse__remove_services"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as stackpulse. Review it before you use it.