Kubernetes MCP connector
The Kubernetes connector brings your clusters' deployments, jobs, autoscalers, certificates and API groups into Elaichi, so Claude, ChatGPT, Cursor, Microsoft Copilot and the Elaichi Agent can read and act on them as the person who signed in.
- Connects with an API key
- Free 14-day trial
- No credit card
Which deployments in the production namespace restarted in the last hour?
Working in Kubernetes with Elaichi
-
Kubernetes service account issuer get openid configuration
-
Kubernetes service account issuer get jwks
-
Kubernetes API discovery get core API versions
How to connect Kubernetes to Claude, ChatGPT, Cursor or Microsoft Copilot
Step by step, for each AI app
Kubernetes 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.
Kubernetes MCP connector for Claude Code
-
1
In a terminal, run
claude mcp addwith the endpoint.https://api.elaichi.ai/mcp -
2
Start Claude Code and run
/mcp. -
3
Pick elaichi, then sign in and approve in the browser.
Terminal
$ claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
Use --scope project instead to share it with the repository through .mcp.json.
Kubernetes 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. The plugin directory lives at chatgpt.com/plugins.
Kubernetes 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.
Kubernetes MCP connector for Microsoft Copilot
-
1
In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
-
2
Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
https://api.elaichi.ai/mcp -
3
Create a new connection, sign in and approve, then press Add to agent.
-
4
Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.
- Server URL
- https://api.elaichi.ai/mcp
- Authentication
- OAuth 2.0
- Type
- Dynamic discovery
Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.
Connect Kubernetes 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.
What teams do with Kubernetes through Elaichi
Ask in plain English. Each person’s AI can do only what they’re allowed to, and every action it takes in Kubernetes is logged.
-
Platform engineering
Check what is running before a change
Ask which deployments and API groups a cluster is serving before you touch it, instead of paging through dashboards and config files.
-
SRE
Find the workload that is misbehaving
During an incident, ask which deployments restarted, which jobs failed and which autoscalers are pinned at their ceiling, in one question from the chat window you already have open.
-
Security
Review certificates and service accounts
Pull up pending certificate requests, the service account issuer's settings and admission rules without handing anyone cluster credentials.
-
Release management
Confirm a rollout landed everywhere
After a release, compare the deployments across namespaces and get a plain list of what is on the new version and what is not.
-
Developer support
Answer is my job done yet
When a developer asks about a batch job, look up its status and recent runs and reply in the same thread.
-
FinOps
See where cluster capacity is going
Ask for replica counts and autoscaler settings by namespace to see which teams are consuming the most, with no spreadsheet export.
Try asking
- “Which deployments in the production namespace restarted in the last hour?”
- “List the batch jobs that failed overnight and why.”
- “Show me pending certificate requests waiting for approval.”
What connecting Kubernetes gets you
6 screens from Elaichi, each doing one job for your Kubernetes account.
Ask Elaichi to work across your apps.
Which deployments in the production namespace restarted in the last hour?
List the batch jobs that failed overnight and why.
Show me pending certificate requests waiting for approval.
Also runs in Claude, ChatGPT, Cursor or Microsoft Copilot
The agent
Ask about your clusters in plain language.
Which deployments restarted, which jobs failed, answered from live Kubernetes records.
Copy the endpoint
AI apps
One governed endpoint for every MCP client.
Claude, ChatGPT and Cursor reach Kubernetes through one org endpoint, no SDK, no shared API key.
Tool catalog
659 Kubernetes tools, no custom code.
Deployments, jobs, autoscalers, certificates and every API group, cataloged and ready to call.
Toolboxes
Every team gets its own Kubernetes toolbox.
Platform engineering sees the whole cluster, developer support sees only what it needs.
Shared connections
Teammates work through a connection, never a key.
One engineer connects Kubernetes, shares it with teams, and nobody else handles the API key.
Audit log
Know who touched which cluster resource.
Every Kubernetes call lands in an append-only log with who, when, what and which resource.
From answering questions to doing the work
A trigger starts the work, inside the same permissions and the same audit log as everything else. Workflows, collections and live dashboards come with the Black plan.
Kubernetes digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch deployments
Kubernetes
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 Jake Morgan
Approve Deny -
Post the digest
Kubernetes
Queued
Workflows
A schedule fires, the digest ships itself.
Failed jobs are fetched, grouped, drafted into a digest, approved by a person, then recorded in Kubernetes.
Kubernetes health
Refreshed 4 minutes ago · every 15 minutes · from the deployments collection
Deployments
1,284 ↓ 12%
Jobs
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Deployments created
Last 14 days
By team
Share of activity
Production 34%
Staging 27%
EU cluster 21%
Platform 18%
Collections and dashboards
Cluster health, computed, not asked for.
Four metrics and a 14 day chart of deployments, by team, with no model involved.
For IT and engineering
Elaichi vs Zapier MCP vs Composio for Kubernetes
All three can connect Kubernetes 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 Kubernetes tools | Allow or restrict single Kubernetes 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 Kubernetes 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 | Free for one person; $15 per user per month on Gold. | 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.
Kubernetes tools for your AI agents
659 tools are ready to call through Elaichi's MCP endpoint the moment you connect Kubernetes, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
Showing 365 of 659 Kubernetes tools here. Connect Kubernetes and call search_tools or tools/list over the MCP endpoint for the complete set.
Questions, answered
How do I connect Kubernetes to Claude?
Connect Kubernetes in Elaichi by pasting your cluster's API key into the connection form, then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. There is no OAuth application to register and no client ID or secret to generate. Claude then signs you in to Elaichi as yourself and can see what your Kubernetes access allows.
Does Kubernetes work with ChatGPT and Cursor as well as Claude?
Yes. Once Kubernetes is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client and the Elaichi Agent. You connect Kubernetes once and every client picks it up.
What can an AI agent actually do with my Kubernetes clusters?
An agent can look up what your Kubernetes clusters are running: deployments, batch jobs, autoscalers, certificate requests, service account settings and the API groups each cluster serves. You ask in plain language, for example which jobs failed overnight, and it answers from the live cluster. Short, concrete asks work better than long sentences.
Does connecting Kubernetes give the AI access to the whole cluster?
No. Access to Kubernetes follows the person who signed in, so an agent sees only the namespaces and resources that person's own Kubernetes permissions allow. Elaichi can narrow that further with roles and restrictions, and it never widens it.
Can I stop an agent from deleting or changing things in Kubernetes?
Yes. In Elaichi you restrict Kubernetes actions one by one, such as deleting a deployment, on a role or on one person. A restricted action still appears in Elaichi's tool search, flagged as restricted, but no client can run it, whatever the prompt says.
What happens to a Kubernetes connection when someone leaves?
Offboarding someone in Elaichi ends their access to Kubernetes at once, across every client they used. A shared Kubernetes connection keeps working for everyone else on the team. If you disconnect Kubernetes in Elaichi, it is removed from every client in one step.
Does the Kubernetes MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Kubernetes 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, Microsoft Copilot, 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 Kubernetes?
Yes. Both let Claude, ChatGPT or Cursor use Kubernetes. 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 Kubernetes call.
How is Elaichi different from Composio for Kubernetes?
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 Kubernetes: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Kubernetes in front of your team
14 days of Black, no credit card. Connect it once and pick what each team can call.
When the trial ends, nothing is deleted. You move to the free Personal plan, and connections, roles and the audit log stay where they are.
Add one link to your AI app
The same link for everyone on your team.
https://api.elaichi.ai/mcp
ChatGPT
Claude
Cursor
Microsoft Copilot