Connectors / Incident Management
Incident Management MCP connectors for Claude, ChatGPT and Cursor
5+ Incident Management connectors in the catalog, each behind the same governed MCP endpoint as everything else in Elaichi.
https://api.elaichi.ai/mcp
The same for every user.
-
Their own access. An agent never gets more than the person it acts for.
-
One connection, every client. Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent.
The connectors
Incident Management connectors in the catalog
Connect one and your whole team reaches it, each inside the access they already have, without anyone handling a credential.
9 connectors
-
Better Stack API key 96 tools
-
Chronosphere API key 2 tools
-
FireHydrant API key 438 tools
-
Freshservice API key 394 tools
-
Freshstatus API key 38 tools
-
incident.io Hosted sign-in 91 tools
-
Instatus API key 96 tools
-
PagerDuty Bring your own OAuth app 157 tools
-
Rootly Hosted sign-in
No Incident Management connector by that name
It may sit under another category, or not be in the catalog yet — any documented API can become a connector.
In practice
What teams do with Incident Management connectors
Drawn from the connector pages in this category, so every line describes something one of these connectors actually does.
Engineering
-
Find out who is on call right now
Ask who is on call for a given service or schedule and get the name straight from PagerDuty, including who picks up next, instead of hunting through rotations.
-
Set up a monitor for a new service
Ask for a monitor on the new checkout URL, checking every minute, and put it in the right monitor group. It is created in Better Stack with the settings you described instead of clicked together by hand.
-
Post the next update from the war room
Ask for the current incident and add the latest update in plain words while the fix is still in progress. Resolve it and set the components back to operational once it is over.
Support
-
Check whether an outage is already open
When customers start reporting problems, ask what active FireHydrant incidents exist right now and what they say, so the support desk answers with the same story engineering is telling.
-
Give customers a straight answer
Ask whether a customer-facing service has an open incident right now and what the current status says, so the reply to the customer matches what engineering actually knows.
-
Post an incident before the tickets pile up
When the same complaint arrives three times in five minutes, open a Freshstatus incident against the affected service and set its status, so customers checking the status page see it before they write in.
IT operations
-
Break a major incident into child tickets
When the VPN goes down, spin one parent ticket into child tickets for networking, identity and communications, and keep the whole thread linked.
-
Answer 'what teams do we have' quickly
Instead of exporting from Chronosphere by hand, ask for the current team list and drop it straight into a runbook, wiki page, or onboarding doc.
-
Review every open incident across services
Pull the list of open and acknowledged incidents across all PagerDuty services, grouped by service or urgency, and get a plain-language summary before the morning standup.
Leadership
-
Prepare the weekly incident review
Pull the incidents from the past week, grouped by severity and service, and get a plain summary ready for the review meeting.
-
Pull last month's uptime numbers
Ask for the availability of every customer-facing monitor over the last thirty days, and for the ones whose response times got slower, ready to paste into the monthly review.
-
See alert trends before the review
Pull alert statistics for the quarter, break them down by tag or source, and ask the telemetry questions you want answered before the operational review starts.
Once it is connected
Things to ask
Each of these is answered against the access the person asking already has, in the Incident Management account you connected.
-
List Better Stack monitors with availability below 99% this week.
-
List every Chronosphere team and its members.
-
List all open FireHydrant incidents from the last seven days.
-
Show open Freshservice tickets raised in the last week.
-
List all services currently showing degraded status.
-
Which alerts fired overnight and which are still unresolved?
-
Which components are degraded right now?
-
Who is on call this weekend across payments schedules?
The tools
What an agent can call in Incident Management
- Connectors
- 5+
- Tools
- 1,312
- Hosted sign-in
- 2
in the Incident Management catalog
callable the moment you connect
connect with nothing to register
Of those 1,312 tools, 15% delete something. Restricting an agent to reads is not a promise here, it is 525 tools admitted and the rest left out — and a restricted tool is never advertised to the model at all.
- Read 40%
- 525 tools · list, get, search
- Write 32%
- 418 tools · create, update, send
- Delete 15%
- 192 tools · delete, remove, archive
- Other 13%
- 177 tools · vendor-specific verbs
One endpoint
https://api.elaichi.ai/mcp
Every connector above answers here.
Every Incident Management connector, by depth
Tool counts are what the connector exposes today; the split is what those tools do.
Hosted sign-in takes a partnership with each vendor, and more are in progress. Until one lands, Your own app means the connector works today — you register an OAuth app once and connect. API key and App credentials mean an admin pastes them once, with nothing to register.
| Connector | Tools | Read · write · delete | Sign-in |
|---|---|---|---|
| FireHydrant | 438 | API key | |
| Freshservice | 394 | API key | |
| PagerDuty | 157 | Your own app | |
| Better Stack | 96 | API key | |
| Instatus | 96 | API key | |
| incident.io | 91 | Hosted | |
| Freshstatus | 38 | API key | |
| Chronosphere | 2 | API key | |
| Rootly | Hosted |
FAQ
Frequently asked questions
How many Incident Management connectors does Elaichi have?
5+ Incident Management connectors are in the catalog today, and the list grows as connectors are added. Each one arrives as a set of MCP tools an agent can call through https://api.elaichi.ai/mcp.
Can Claude, ChatGPT and Cursor all use Incident Management connectors?
Yes. Elaichi exposes one organization-wide endpoint, https://api.elaichi.ai/mcp, and Claude, ChatGPT, Cursor or any MCP client connects to that same address with OAuth, while the Elaichi Agent reaches the same tools inside the app. Connecting a Incident Management account once makes it reachable from every one of them.
Do Incident Management connectors work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Incident Management connectors are reached over the same MCP endpoint every client uses, so anything that speaks MCP can call them — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor and the Elaichi Agent. There is no per-client setup beyond pointing the client at https://api.elaichi.ai/mcp.
Do Incident Management connectors need me to bring my own OAuth app?
Most do not. 2 of the Incident Management connectors use Elaichi's hosted sign-in, with nothing to register. 6 connect with an API key or app credentials that an admin pastes once, with no app to register. 1 asks you to bring your own OAuth app: you register it once with the vendor and connect. Hosted sign-in for those is in progress, a vendor partnership at a time, and when one lands the only thing that changes is that the registration step goes away. Each connector's page says which it is before you start.
Can I stop an agent from writing to Incident Management tools?
Yes. Tool restrictions apply at role and individual level, and a restricted tool is left out of the model's tool list and cannot be called. Read-only access to a Incident Management connector is a matter of allowing the reads and leaving the writes out.
Nearby
Teams that connect Incident Management usually connect these too
Put Incident Management connectors in front of your team
14 days on Gold, no credit card. Connect one and pick what each team can call.
- Works with
-
and any other MCP client, or the Elaichi Agent.
- When the trial ends
- Nothing is deleted. Connections, roles and the audit log stay where they are, so subscribing picks up exactly where you left off.