Application Development
Portainer MCP connector
The Portainer connector lets Claude, ChatGPT, Cursor, and the Elaichi Agent look at the containers, Kubernetes applications, cron jobs, ingresses, and node metrics in your Portainer environments, with every call tied to 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 Portainer to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Portainer once
-
Open Connections, choose Add connection, and pick Portainer.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a Portainer API key. One person generates a token in Portainer 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 Portainer 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 Portainer 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 Portainer 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 Portainer 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 Portainer through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Platform engineering
See what is running before a change
Ask which Kubernetes applications are deployed in each Portainer environment, how many there are, and how their resources look before you touch anything.
-
Operations
Check cluster health from a chat window
Pull node metrics and per-application resource usage from Portainer to find out what is running hot, without opening a dashboard first.
-
DevOps
Clean up finished jobs and cron jobs
List the jobs and cron jobs in a Portainer environment, spot the stale ones, and remove them by ID when the person asking is allowed to.
-
Security
Review who holds which cluster role
List Portainer roles, cluster roles, and cluster role bindings to see who can do what, and remove a binding that should not be there.
-
Networking
Audit ingresses and ingress controllers
Find out which ingresses exist, how many there are, and which controllers serve them, then update controller settings in bulk when policy changes.
-
Development
Look up a config map without kubectl
Ask what config maps a Portainer environment holds and get a plain description of an application when something in staging looks wrong.
Try asking
- “List Portainer applications by cluster and show restart counts.”
- “Which cron jobs ran in the production Portainer environment?”
- “Summarize Portainer cluster roles and who they are bound to.”
AI tools
Portainer tools for your AI agents
256 tools are ready to call through Elaichi's MCP endpoint the moment you connect Portainer, 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 Portainer gets you
6 screens from the product, each doing one job for your Portainer account.
The agent
Ask about clusters, get real answers.
Type a question in plain language and read it back from live Portainer records.
- applications
- cron jobs
- configmaps
- cluster roles
Ask Elaichi to work across your apps.
List Portainer applications by cluster and show restart counts.
Which cron jobs ran in the production Portainer environment?
Summarize Portainer cluster roles and who they are bound to.
Also runs in Claude, ChatGPT or Cursor
MCP clients
Claude, ChatGPT and Cursor connect here.
One governed Portainer endpoint over OAuth, no SDK and no shared API key.
Copy the endpoint
Tool catalog
256 Portainer tools ready to call.
Applications, cron jobs, configmaps and cluster roles covered with no custom code.
- List all Portainer roles
- List all Portainer kubernete applications
- List all Portainer applications counts
- Delete a Portainer cluster role bindings delete by ID
Toolboxes
Every team gets its own toolbox.
Platform, SRE and app teams each hold a Portainer toolbox scoped to them.
- Platform
- SRE
- Application development
- Security
Shared connections
Share Portainer access, never the credential.
See who connected each account and how many teams and members use it.
- Production
- Staging
- Platform EMEA
- Edge sites
Audit log
Every Portainer call is on record.
When, who, what happened, type and resource, appended and never edited.
- 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, work finishes itself.
Fetch Portainer applications, group them, draft a digest, approve, post it back.
Portainer digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch applications
Portainer
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
Portainer
Queued
Collections and dashboards
Portainer health arrives before you ask.
Four metrics, 14 days of records created, split by team, refreshed on schedule.
Portainer health
Refreshed 4 minutes ago · every 15 minutes · from the applications collection
Applications
1,284 ↓ 12%
Cron jobs
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Applications created
Last 14 days
By team
Share of activity
Production 34%
Staging 27%
Platform EMEA 21%
Edge sites 18%
FAQ
Frequently asked questions
How do I connect Portainer to Claude?
Connect Portainer inside Elaichi first, then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp as the endpoint. Portainer connects with an API key, which is a token you create in your Portainer account settings and paste into Elaichi once. There is no OAuth application to register and no client ID or secret to generate. The whole thing takes a few minutes.
Does Portainer work with ChatGPT and Cursor as well as Claude?
Yes. Once Portainer 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 Portainer once and every client you sign into can use it.
What can an AI agent actually do with my Portainer data?
It can list the Kubernetes applications, config maps, cron jobs, jobs, ingresses, and ingress controllers in your Portainer environments, read node and application metrics, and describe roles and cluster role bindings. Where you allow it, it can also delete a job, cron job, ingress, or cluster role binding by ID and update ingress controllers in bulk. Portainer exposes a lot through this connector, so short concrete asks like "list cron jobs in production" work better than long paragraphs.
Does connecting Portainer give the AI access to every environment?
No. The AI acts inside the access of whoever signed into Portainer, so it can only see the environments and Kubernetes resources that person's Portainer role already allows. Elaichi can narrow that further, for example to read-only, but it can never widen what Portainer itself grants.
Can I stop an agent from deleting or changing things in Portainer?
Yes. Restrictions in Elaichi work per action, so you can allow listing applications and reading metrics in Portainer while blocking every delete and bulk update. A blocked action is never shown to Claude, ChatGPT, or Cursor at all, so no prompt, however worded, can reach it.
What happens to a Portainer connection when someone leaves?
Offboarding that person in Elaichi ends their access to Portainer through every AI client at once. If the Portainer connection was shared with a team, it keeps working for everyone else. Disconnecting Portainer once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client together.
Put Portainer in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.