Better Stack MCP connector
Connect Better Stack to Claude, ChatGPT, Cursor, or any MCP client through Elaichi, and check monitor uptime, response times, heartbeats, and on-call schedules in plain language, with every action logged under the person who asked.
-
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 Better Stack to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Better Stack once
-
Open Connections, choose Add connection, and pick Better Stack.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a Better Stack API key. One person generates a token in Better Stack 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.
Better Stack 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.
Better Stack 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.
Better Stack 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 Better Stack 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 Better Stack through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Engineering
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.
-
Support
Confirm whether a site is actually down
When a customer reports an outage, ask what the monitor for that page shows right now and how its response times have looked over the past hour, then reply with facts instead of a guess.
-
Operations
Find out who is on call right now
Ask which on-call schedule covers this hour and who is holding the pager before escalating a problem, without opening Better Stack to find the rota.
-
Platform
Catch a nightly job that stopped reporting
Ask which heartbeats have gone quiet since yesterday, and set up a new heartbeat for the backup job that nobody was watching.
-
Engineering
Tidy monitors and heartbeats into groups
Ask for every unassigned monitor to be sorted into groups by product or region, and rename the groups that no longer match how the team is organized.
-
Leadership
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.
Try asking
- “List Better Stack monitors with availability below 99% this week.”
- “Which heartbeats missed a check in the last day?”
- “Summarize incidents by monitor group for the on call handover.”
Compare
Elaichi vs Zapier MCP vs Composio for Better Stack
All three can connect Better Stack 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 Better Stack tools | Allow or restrict single Better Stack 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 Better Stack 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
Better Stack tools for your AI agents
96 tools are ready to call through Elaichi's MCP endpoint the moment you connect Better Stack, 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 Better Stack gets you
6 screens from the product, each doing one job for your Better Stack account.
The agent
Ask about monitors, get live answers.
Plain language questions read straight from Better Stack monitors, heartbeats and incidents.
- monitors
- monitor groups
- heartbeats
- incidents
Ask Elaichi to work across your apps.
List Better Stack monitors with availability below 99% this week.
Which heartbeats missed a check in the last day?
Summarize incidents by monitor group for the on call handover.
Also runs in Claude, ChatGPT or Cursor
MCP clients
Claude, ChatGPT and Cursor, one endpoint.
Every client reaches Better Stack over OAuth through one org endpoint, no shared key.
Copy the endpoint
Tool catalog
96 Better Stack tools, no custom code.
Monitors, monitor groups, heartbeats and incidents, each with list, read and write methods.
- List all Better Stack monitors
- Get single Better Stack monitor by ID
- Create a Better Stack monitor
- Update a Better Stack monitor by ID
Toolboxes
Every team gets its own toolbox.
Scope Better Stack monitor and heartbeat tools per team, from on call to platform.
- On call
- Platform
- SRE
- Support
Shared connections
Share the connection, never the credential.
Teammates run Better Stack calls through a connection while the token stays hidden.
- Production
- Staging
- Platform EMEA
- On call
Audit log
Answer who paused which monitor.
Every Better Stack call lands append only with time, actor, event and resource.
- 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, the digest ships.
Fetch Better Stack incidents, group them, draft a digest, approve, post it back.
Better Stack digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch monitors
Better Stack
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
Better Stack
Queued
Collections and dashboards
Monitor health, counted not summarized.
Four metrics, 14 days of Better Stack incidents and a team breakdown, refreshed on schedule.
Better Stack health
Refreshed 4 minutes ago · every 15 minutes · from the monitors collection
Monitors
1,284 ↓ 12%
Monitor groups
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Monitors created
Last 14 days
By team
Share of activity
Production 34%
Staging 27%
Platform EMEA 21%
On call 18%
FAQ
Frequently asked questions
How do I connect Better Stack to Claude?
In Elaichi, open Connectors, choose Better Stack, and paste in an API key from your Better Stack account when asked. There is no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste the endpoint https://api.elaichi.ai/mcp. Claude will ask you to sign in to Elaichi as yourself, and Better Stack is available from then on.
Does Better Stack work with ChatGPT and Cursor as well as Claude?
Yes. Once Better Stack 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 Better Stack once and every client you use picks it up.
What can an AI agent actually do with my Better Stack data?
With Better Stack connected, you can ask which monitors are down, how a site's response times have trended, which heartbeats have stopped reporting, and who is on the current on-call schedule. You can also ask it to create, change, or remove monitors, heartbeats, and the groups they sit in. Because Better Stack exposes many actions, short concrete asks like "show availability for the API monitor this week" work better than long paragraphs.
Does connecting Better Stack give the AI access to everything in my account?
No. The AI works inside the access of the person who connected Better Stack, so it can only see the monitors, heartbeats, and on-call schedules that person's Better Stack API key can already reach. Elaichi can narrow that access further with restrictions, and it can never widen it beyond what Better Stack itself allows.
Can I stop an agent from deleting or changing things in Better Stack?
Yes. In Elaichi, restrictions on the Better Stack connector apply per action, so you can allow reading monitor availability and response times while blocking anything that deletes or updates a monitor, heartbeat, or group. A blocked action is never shown to Claude, ChatGPT, Cursor, or any other client at all, so no prompt, accidental or otherwise, can reach it.
What happens to a Better Stack connection when someone leaves?
When you offboard someone in Elaichi, their access to Better Stack through every AI client ends at once. If they had shared a Better Stack connection with a team, it keeps working for everyone else on that team. If you want to remove Better Stack entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other connected client.
Does the Better Stack MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Better Stack 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 Better Stack?
Yes. Both let Claude, ChatGPT or Cursor use Better Stack. 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 Better Stack call.
How is Elaichi different from Composio for Better Stack?
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 Better Stack: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Better Stack 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.