Incident Management
FireHydrant MCP connector
The FireHydrant connector lets Claude, ChatGPT, Cursor and other MCP clients open, update and list FireHydrant incidents, alerts and change events, with each person working inside their own FireHydrant access and every action recorded.
-
How it connects. Connects with an API key. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
How to connect
How to connect FireHydrant to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect FireHydrant once
-
Open Connections, choose Add connection, and pick FireHydrant.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a FireHydrant API key. One person generates a token in FireHydrant and pastes it once. Everyone else works through Share with, and never sees it.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Connect FireHydrant to Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Connect FireHydrant to ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Connect FireHydrant to Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect FireHydrant to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with FireHydrant through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
On-call engineering
Open an incident from a paging alert
When an alert fires, ask the agent to open a FireHydrant incident with the right title and severity instead of filling in the form under pressure. It can also tie the triggering alert to the new incident.
-
Incident command
Catch the incident up during the bridge
While the call is running, tell the agent what changed and it updates the FireHydrant incident with the new status, severity or summary. Nobody has to break away from the conversation to type it in.
-
Platform and SRE
Log a deploy as a change event
After a rollout, ask the agent to record a FireHydrant change event with what shipped and when, so the timeline is there when something breaks an hour later.
-
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.
-
Engineering management
Summarize last week's incidents and alerts
Ask for every FireHydrant incident from the past seven days, grouped by severity, or which alerts fired most often. The agent lists them from live records rather than a stale export.
-
Release management
Line up changes against a failure
Ask which FireHydrant change events landed in the two hours before an incident opened, so the team can rule causes in or out quickly.
Try asking
- “List all open FireHydrant incidents from the last seven days.”
- “Which services had the most change events this month?”
- “Summarize yesterday's FireHydrant incidents by severity and owning team.”
AI tools
FireHydrant tools for your AI agents
438 tools are ready to call through Elaichi's MCP endpoint the moment you connect FireHydrant, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
See it in Elaichi
What connecting FireHydrant gets you
6 screens from the product, each doing one job for your FireHydrant account.
The agent
Ask about incidents, read the answer.
Plain language questions return live FireHydrant incidents, change events and services.
- incidents
- change events
- services
- entitlements
Ask Elaichi to work across your apps.
List all open FireHydrant incidents from the last seven days.
Which services had the most change events this month?
Summarize yesterday's FireHydrant incidents by severity and owning team.
Also runs in Claude, ChatGPT or Cursor
MCP clients
Claude, ChatGPT and Cursor reach FireHydrant.
One org MCP endpoint over OAuth, no SDK and no shared API key.
Copy the endpoint
Tool catalog
438 FireHydrant tools ready to call.
Incidents, change events and entitlements are covered without a line of custom code.
- Create a FireHydrant change event
- Delete a FireHydrant change event by ID
- Get single FireHydrant change event by ID
- List all FireHydrant change events
Toolboxes
Every team gets its own toolbox.
On call, engineering and support each see a FireHydrant toolbox scoped to them.
- On call
- Platform engineering
- Support
- SRE
Shared connections
Teammates run incidents without a credential.
Each FireHydrant connection shows who added it and which teams and members share it.
- Production
- On call EMEA
- Support
- Platform
Audit log
Every incident call has a name on it.
When, who, what happened, type and resource for each FireHydrant request.
- When
- Who
- What happened
- Type
Launching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule fires, a digest ships.
Six steps fetch FireHydrant incidents, group them, draft a digest, await approval, post back.
FireHydrant digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch incidents
FireHydrant
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
FireHydrant
Queued
Collections and dashboards
Incident health arrives before anyone asks.
Four metrics, 14 days of incidents created and a team breakdown, computed on schedule.
FireHydrant health
Refreshed 4 minutes ago · every 15 minutes · from the incidents collection
Incidents
1,284 ↓ 12%
Change events
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Incidents created
Last 14 days
By team
Share of activity
Production 34%
On call EMEA 27%
Support 21%
Platform 18%
FAQ
Frequently asked questions
How do I connect FireHydrant to Claude?
Connecting FireHydrant to Claude takes two steps. First, connect FireHydrant in Elaichi by pasting a FireHydrant API key when asked; there is no OAuth application to register and no client ID or secret to generate. Then in Claude, open Customize, then Connectors, then Add, and paste the endpoint https://api.elaichi.ai/mcp. Sign in with your Elaichi account and FireHydrant incidents, alerts and change events are available in your conversation.
Does FireHydrant work with ChatGPT and Cursor as well as Claude?
Yes. Once FireHydrant is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect FireHydrant once and every client you use gets it.
What can an AI agent actually do with my FireHydrant data?
With FireHydrant connected, an agent can open a new incident, update its severity, status or summary, and pull up any incident by name or list the ones currently open. It can record change events such as deploys and configuration changes, look up alerts and attach them to incidents, and read the processing log when you want to know how a signal was handled. Short, specific asks such as "open a sev2 for the checkout API" work better than long paragraphs, because the agent searches for the right FireHydrant action based on what you ask.
Does connecting FireHydrant give the AI access to every incident in my organization?
No. When you connect FireHydrant through Elaichi, the agent works with the access of the API key you provided and the person who signed in, so it sees the FireHydrant incidents, alerts and change events that person can already see and nothing more. Elaichi can narrow that access further, for example to reading only, but it can never widen it beyond what FireHydrant itself allows.
Can I stop an agent from deleting or changing incidents in FireHydrant?
Yes. Restrictions in Elaichi apply per action, so you can allow reading FireHydrant incidents and alerts while blocking deleting incidents, removing change events or editing alerts. A blocked action is never advertised to Claude, ChatGPT or any other client, so no prompt, accidental or otherwise, can reach it.
What happens to a FireHydrant connection when someone leaves?
When you offboard a person in Elaichi, their access to FireHydrant through every connected client ends at once. If they connected FireHydrant and shared it with a team, the shared connection keeps working for everyone else. Disconnecting FireHydrant once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client at the same time.
Put FireHydrant in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.