incident.io MCP connector
The incident.io connector brings incidents, alerts, follow-up actions, on-call cover requests, and your service catalog to Claude, ChatGPT, Cursor, and the Elaichi Agent, so each person can ask about and update live incidents inside their own incident.io access.
-
How it connects. Connects over OAuth. 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.
91 tools
How to connect
How to connect incident.io to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect incident.io once
-
Open Connections, choose Add connection, and pick incident.io.
-
Optionally set Share with to give a team access, then press Connect.
-
Approve it in incident.io. incident.io's own window opens. Whoever approves it decides what this connection can reach.
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.
incident.io MCP connector for 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.
incident.io MCP connector for 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.
incident.io MCP connector for 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 incident.io 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 incident.io through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Engineering
Catch up on an incident fast
Ask what an incident.io incident is about, what has happened so far, and what is still open, without scrolling the whole timeline. The answer comes from the live record, not from memory.
-
Platform
Triage overnight alerts in one pass
List the alerts that fired overnight, see which sources they came from, attach the related ones to an existing incident, and resolve the noise. Spin up a new incident from an alert when it turns out to be real.
-
Engineering
Keep follow-up actions honest
Create the actions agreed on the call, update them as work lands, and list what is still unassigned before the review meeting.
-
Support
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.
-
On-call
Sort out cover for the weekend
Raise a cover request when you cannot take a shift, see who else has asked, and approve or decline requests from your team without opening the schedule.
-
Leadership
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.
Try asking
- “Which alerts fired overnight and which are still unresolved?”
- “List the open actions on the checkout latency incident.”
- “Show pending cover requests for this weekend's on-call shifts.”
Compare
Elaichi vs Zapier MCP vs Composio for incident.io
All three can connect incident.io to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.
| What to check | Elaichi | Zapier MCP | Composio |
|---|---|---|---|
| Where the AI connects |
One address for the whole organization.
https://api.elaichi.ai/mcp
|
A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over incident.io tools | Allow or restrict single incident.io tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per incident.io call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. |
Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.
Longer take: Zapier MCP alternative and when you don't need an MCP gateway.
AI tools
incident.io tools for your AI agents
91 tools are ready to call through Elaichi's MCP endpoint the moment you connect incident.io, governed by the same roles, restrictions, and audit log as everything else in Elaichi. incident.io builds and runs these tools.
No tools match your search.
See it in Elaichi
What connecting incident.io gets you
6 screens from the product, each doing one job for your incident.io account.
The agent
Ask what broke and get the live answer.
Ask about an incident.io incident, alert, or action in plain language and get current records back.
- incidents
- alerts
- actions
- cover requests
Ask Elaichi to work across your apps.
Which alerts fired overnight and which are still unresolved?
List the open actions on the checkout latency incident.
Show pending cover requests for this weekend's on-call shifts.
Also runs in Claude, ChatGPT or Cursor
MCP clients
One governed endpoint reaches every MCP client.
Claude, ChatGPT, and Cursor work incident.io incidents through one org endpoint, no SDK, no shared key.
ElaichiMCP clientsClaude
ChatGPT
Cursor
Copy the endpoint
Tool catalog
91 incident.io tools, no code to write.
Incidents, alerts, actions, cover requests, and catalog entries covered without writing a line of code.
- Action create
- Action delete
- Action list
- Action update
ElaichiToolsToolboxes
Every team gets its own incident.io toolbox.
Scope platform to alerts, engineering to actions, support to incident status, leadership to statistics.
- Engineering
- Platform
- Support
- Security
ElaichiToolboxesShared connections
Share the connection, never the credential.
One person connects incident.io, shares it with teams, and nobody else ever handles a token.
- Platform
- Payments
- Support
- Security
ElaichiConnectionsAudit log
Every incident.io call is written down.
See who resolved which alert, when, and from which client, in an append-only log.
- When
- Who
- What happened
- Type
ElaichiAudit logLaunching 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 starts the work, a person approves.
Open incident.io actions are fetched, grouped, drafted into a digest, approved, then posted back.
incident.io digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch incidents
incident.io
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
incident.io
Queued
Collections and dashboards
Incident numbers refresh without anyone asking.
Incidents opened over 14 days, alert volume, and team breakdown, computed with no model involved.
incident.io health
Refreshed 4 minutes ago · every 15 minutes · from the incidents collection
Incidents
1,284 ↓ 12%
Alerts
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Incidents created
Last 14 days
By team
Share of activity
Platform 34%
Payments 27%
Support 21%
Security 18%
FAQ
Frequently asked questions
How do I connect incident.io to Claude?
Connect incident.io in Elaichi first: pick it from the catalog, and incident.io shows its own approval screen asking you to allow access to your account, since it connects over OAuth. There is no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Sign in as yourself and incident.io is ready in Claude.
Does incident.io work with ChatGPT and Cursor as well as Claude?
Yes. Once incident.io 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 incident.io once and every client picks it up.
What can an AI agent actually do with my incident.io data?
With incident.io connected, an agent can tell you what an incident is about and what is still open, list and resolve alerts, attach alerts to incidents or open a new incident from one, and create or update follow-up actions. It can also look up services in your catalog, handle on-call cover requests, and pull alert statistics. Short, concrete asks such as "list unresolved alerts from the payments source" work better than long paragraphs.
Does connecting incident.io give the AI access to every incident and alert?
No. Every call to incident.io runs as the person who signed in, so the agent sees only the incidents, alerts, and catalog entries that person can already see in incident.io. Elaichi can narrow that further for a team, for example read-only on incidents, but it can never widen it beyond what incident.io itself allows that person.
Can I stop an agent from deleting or changing things in incident.io?
Yes. Restrictions in Elaichi apply per action, so you can allow reading incidents and alerts while blocking deleting actions or resolving alerts for a given team. A restricted action is never advertised to Claude, ChatGPT, or Cursor at all, so no prompt, however worded, can reach it in incident.io.
What happens to an incident.io connection when someone leaves?
Offboarding a person in Elaichi ends their access to incident.io through every client at once, including Claude, ChatGPT, and Cursor. A connection they shared keeps working for everyone else on the team. If you want to remove incident.io entirely, disconnecting it once in Elaichi removes it from every client.
Does the incident.io MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. incident.io is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.
Is Elaichi an alternative to Zapier MCP for incident.io?
Yes. Both let Claude, ChatGPT or Cursor use incident.io. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every incident.io call.
How is Elaichi different from Composio for incident.io?
Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to incident.io: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put incident.io in front of your team
14 days on Gold, no credit card. Connect it once 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.