# Portainer MCP connector

The Portainer connector lets Claude, ChatGPT, Cursor, Microsoft Copilot, 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.

Source: https://elaichi.ai/connectors/portainer/

## Facts

| | |
| --- | --- |
| Application | Portainer |
| Category | Application Development |
| AI tools | 256 |
| Authentication | Connects with an API key |
| Bring your own OAuth app | No |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Portainer is connected

- 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.

## Connect Portainer in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Portainer.
2. Optionally set Share with, then press Connect.
3. 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.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Portainer tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Portainer MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Portainer MCP connector for Claude Code

Endpoint: https://api.elaichi.ai/mcp

1. In a terminal, run `claude mcp add` with the endpoint.
2. Start Claude Code and run `/mcp`.
3. Pick elaichi, then sign in and approve in the browser.

```bash
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`.

## Portainer MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
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.

## Portainer MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Portainer MCP connector for Microsoft Copilot

Endpoint: https://api.elaichi.ai/mcp

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.
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.

Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.

## Connect Portainer to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Every scope the client asks for starts ticked except "Delete data and remove access", which you tick yourself. Calling a Portainer tool needs "Run your connected tools". Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Think hard before granting Run your connected tools, which can also delete in connected apps and cannot be undone.

## What teams do with Portainer through Elaichi

### See what is running before a change

Platform engineering. Ask which Kubernetes applications are deployed in each Portainer environment, how many there are, and how their resources look before you touch anything.

### Check cluster health from a chat window

Operations. Pull node metrics and per-application resource usage from Portainer to find out what is running hot, without opening a dashboard first.

### Clean up finished jobs and cron jobs

DevOps. 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.

### Review who holds which cluster role

Security. List Portainer roles, cluster roles, and cluster role bindings to see who can do what, and remove a binding that should not be there.

### Audit ingresses and ingress controllers

Networking. Find out which ingresses exist, how many there are, and which controllers serve them, then update controller settings in bulk when policy changes.

### Look up a config map without kubectl

Development. Ask what config maps a Portainer environment holds and get a plain description of an application when something in staging looks wrong.

## Elaichi vs Zapier MCP vs Composio for Portainer

All three can connect Portainer 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. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Portainer tools | Allow or restrict single Portainer 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 Portainer 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](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## 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, Microsoft Copilot, 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 my team share one Portainer connection?

Yes. One person connects Portainer in Elaichi and shares it with a team, and nobody else ever handles the Portainer API key. Each teammate still signs in to Elaichi as themselves, so every call to Portainer is logged under their own name.

### 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 restricting every delete and bulk update. A restricted action still appears in Elaichi's tool search, flagged as restricted, but Claude, ChatGPT, Cursor or Microsoft Copilot cannot run it, whatever the prompt says.

### 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, Microsoft Copilot, and every other client together.

### Does the Portainer MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Portainer 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 Portainer?

Yes. Both let Claude, ChatGPT or Cursor use Portainer. 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 Portainer call.

### How is Elaichi different from Composio for Portainer?

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 Portainer: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 256 Portainer tools

Every tool below is callable through https://api.elaichi.ai/mcp once Portainer is connected, subject to the toolbox it is in and the restrictions on the caller.

- **List all Portainer roles** (List). List all Portainer roles available for use. Returns an array of role objects including id, name, description, and priority.
- **List all Portainer kubernete applications** (List). List Kubernetes applications across all namespaces in a Portainer environment. When nodeName is provided, returns only applications running on that node. Returns an array of application objects, each with an id and schema-specific attributes defined in the upstream K8sApplication schema. Required: kubernete_id, namespace, nodeName.
- **List all Portainer applications counts** (List). Get the count of Kubernetes applications across all namespaces in a Portainer environment. Returns an integer count of applications, optionally filtered to a specific node when nodeName is supplied. Required: kubernete_id.
- **Delete a Portainer cluster role bindings delete by ID** (Delete). Delete a list of cluster role bindings from a Portainer Kubernetes environment. Accepts an array of cluster role binding names to remove. Returns an empty 204 response on success. Required: kubernete_id (the environment identifier) and a JSON array of cluster role binding names in the request body.
- **Delete a Portainer cluster roles delete by ID** (Delete). Delete a list of Kubernetes cluster roles in a Portainer environment. Returns an empty 204 response on success. Required: kubernete_id and a request body array of cluster role names.
- **List all Portainer kubernete clusterrolebindings** (List). List Kubernetes cluster role bindings within a Portainer environment at the cluster level. Returns each binding's name and attributes. Required: kubernete_id.
- **List all Portainer kubernete clusterroles** (List). List Kubernetes cluster roles within a Portainer environment at the cluster level. Returns an array of K8sClusterRole objects including id and attributes whose field-level shape is defined in the upstream OpenAPI schema. Required: kubernete_id.
- **List all Portainer kubernete configmaps** (List). List ConfigMaps across all namespaces in a Portainer Kubernetes environment. Returns an array of K8sConfigMap objects; when isUsed is set to true, each item includes information about applications that use it. Required: kubernete_id, isUsed.
- **List all Portainer configmaps counts** (List). Get the count of ConfigMaps across all namespaces in a Portainer Kubernetes environment. Returns an integer count of ConfigMaps; for non-admin users only ConfigMaps in accessible namespaces are counted. Required: kubernete_id.
- **List all Portainer kubernete cron jobs** (List). List Kubernetes Cron Jobs in a Portainer environment that the authenticated user has access to. Returns an array of Cron Job objects. Required: kubernete_id.
- **Delete a Portainer cron jobs delete by ID** (Delete). Delete Kubernetes Cron Jobs from a Portainer environment, grouped by namespace. Returns an empty 204 response on success. Required: kubernete_id and a request body mapping each namespace to an array of Cron Job names to delete.
- **List all Portainer kubernete dashboards** (List). Get Kubernetes dashboard summary data for a Portainer environment, providing counts of commonly used Kubernetes resources. Returns an array of dashboard summary objects whose fields are defined by the upstream K8sDashboard schema (resource counts). Required: kubernete_id.
- **List all Portainer kubernete describes** (List). Get a description of a Kubernetes resource in a Portainer environment. Returns the resource description with content-type-specific fields that vary by resource kind. Required: kubernete_id, name, kind.
- **List all Portainer kubernetes** (List). List Kubernetes events in a Portainer environment, optionally filtered by the resource id of a specific involved Kubernetes object. Returns Kubernetes event objects with an id and attributes whose fields are defined upstream in the kubernetes.K8sEvent schema. Required: kubernete_id.
- **List all Portainer kubernete ingresscontrollers** (List). List Kubernetes ingress controllers for a Portainer environment, optionally filtering to only allowed controllers. Returns: attributes (ingress controller fields defined by the upstream kubernetes.K8sIngressController schema). Required: kubernete_id.
- **Portainer kubernete ingresscontrollers bulk update** (Update). Update (block/unblock) Kubernetes ingress controllers for a Portainer environment by submitting an array of ingress controller objects. Returns an empty 204 response on success. Required: kubernete_id.
- **List all Portainer kubernete ingresses** (List). List Kubernetes ingresses at the cluster level for a Portainer environment. Returns ingress records including id and attributes with fields defined in the upstream K8sIngressInfo schema. Required: kubernete_id.
- **List all Portainer ingresses counts** (List). Get the count of Kubernetes ingresses within a specific Portainer environment. Returns an integer representing the total number of ingresses. Required: kubernete_id.
- **Delete a Portainer ingresses delete by ID** (Delete). Delete one or more Kubernetes Ingresses in a Portainer environment. Returns an empty 204 response on success. Required: kubernete_id.
- **List all Portainer kubernete jobs** (List). List Kubernetes Jobs in a Portainer environment that the authenticated user has access to. Optionally include jobs owned by cron jobs. Returns: id. Required: kubernete_id.
- **Delete a Portainer jobs delete by ID** (Delete). Delete a list of Kubernetes Jobs in a Portainer environment by providing a namespace-to-jobs map. Returns an empty 204 response on success. Required: kubernete_id (environment identifier) and a request body mapping namespace names to arrays of Job names.
- **List all Portainer kubernete max resource limits** (List). Get max CPU and memory limits (unused resources) for all nodes within a Kubernetes cluster in Portainer. Returns a map of per-node resource limits including CPU and memory capacity per node. Required: kubernete_id.
- **List all Portainer metrics applications resources** (List). List the total CPU (cores) and memory (bytes) requests and limits of all applications across all namespaces in a Portainer Kubernetes environment. Returns: CpuRequest, CpuLimit, MemoryRequest, MemoryLimit. Required: kubernete_id, node.
- **List all Portainer metrics nodes** (List). List live metrics for all nodes in a Portainer Kubernetes environment. Returns the NodeMetricsList object whose field shape is defined by the Kubernetes v1beta1.NodeMetricsList schema referenced upstream. Required: kubernete_id.
- **Get single Portainer metrics node by ID** (Get). Get live metrics for a specific node by id in a Portainer Kubernetes environment. Returns: apiVersion, kind, metadata, timestamp, window, usage. Required: kubernete_id, id.
- **List all Portainer metrics pods** (List). List pods with their live metrics in a Portainer Kubernetes environment namespace. Returns a v1beta1.PodMetricsList whose fields are defined by the upstream Kubernetes metrics API and are not expanded in the Portainer API documentation. Required: kubernete_id, namespace.
- **Get single Portainer metrics pod by ID** (Get). Get live metrics for a specific pod in a Portainer Kubernetes environment namespace. Returns a v1beta1.PodMetrics object whose fields are defined by the upstream Kubernetes metrics API and are not expanded in the Portainer API documentation. Required: kubernete_id, namespace, id.
- **List all Portainer kubernete namespaces** (List). List all Kubernetes namespaces in a Portainer environment, scoped by the user's role and permissions. Returns: Name. Required: kubernete_id, withResourceQuota, withUnhealthyEvents.
- **Create a Portainer kubernete namespace** (Create). Create a Kubernetes namespace in a Portainer environment. Returns: Name. Required: kubernete_id, Name.
- **Update a Portainer kubernete namespace by ID** (Update). Update a Kubernetes namespace in a Portainer environment. Returns: Name. Required: kubernete_id, id, Name.
- **Portainer kubernete namespaces list events** (List). List Kubernetes events for a namespace in a Portainer environment, optionally filtered by resource id. Returns: id. Required: kubernete_id, namespace.
- **Get single Portainer kubernete namespace by ID** (Get). Get details of a Kubernetes namespace in a Portainer environment by id. Returns: id, attributes. Required: kubernete_id, id.
- **Portainer kubernete namespaces bulk update** (Update). Update Kubernetes namespaces within a Portainer environment. Returns: id, attributes. Required: kubernete_id.
- **Portainer kubernete namespaces bulk delete** (Delete). Delete a Kubernetes namespace in a Portainer environment. Returns a success message string. Required: kubernete_id, namespace.
- **List all Portainer namespace configmaps** (List). Get a ConfigMap by name within a specific namespace in a Portainer Kubernetes environment. Returns the full Kubernetes ConfigMap object including its name, namespace, and configuration data. Required: kubernete_id, namespace, configmap.
- **List all Portainer namespace ingresscontrollers** (List). List ingress controllers for a Portainer Kubernetes environment in a specific namespace. Returns an array of ingress controller objects with attributes defined by the upstream K8sIngressController schema. Required: kubernete_id, namespace.
- **Portainer namespace ingresscontrollers bulk update** (Update). Update (block/unblock) Kubernetes ingress controllers by namespace for a Portainer environment. Accepts an array of ingress controller objects to update. Returns an empty 204 response on success. Required: kubernete_id, namespace.
- **List all Portainer namespace ingresses** (List). List Kubernetes ingresses in a specific namespace within a Portainer environment. Returns: id, name. Required: kubernete_id, namespace.
- **Create a Portainer namespace ingress** (Create). Create a Kubernetes ingress in a specific namespace within a Portainer environment. Returns an empty 204 response on success. Required: kubernete_id, namespace.
- **Get single Portainer namespace ingress by ID** (Get). Get a single Kubernetes ingress by id in a specific namespace within a Portainer environment. Returns: id, name, namespace. Required: kubernete_id, namespace, id.
- **Portainer namespace ingresses bulk update** (Update). Update a Kubernetes ingress in a specific namespace within a Portainer environment. Returns an empty 204 response on success. Required: kubernete_id, namespace.
- **List all Portainer namespace persistent volume claims** (List). List Kubernetes PersistentVolumeClaims in a namespace within a Portainer environment. Returns PVC objects including name and attributes. Required: kubernete_id, namespace.
- **Get single Portainer namespace persistent volume claim by ID** (Get). Get a specific PersistentVolumeClaim by name within a Kubernetes namespace in a Portainer environment. Returns the PVC object including its id and attributes. Required: kubernete_id, namespace, id.
- **Delete a Portainer namespace pod by ID** (Delete). Delete a Kubernetes pod in a given namespace from Portainer. The owning controller (Deployment, StatefulSet, DaemonSet) recreates the pod; naked pods are removed permanently. Returns an empty 204 response on success. Required: kubernete_id, namespace, id.
- **Create a Portainer pod restart** (Create). Restart all containers in a Kubernetes pod in place using the Kubernetes 1.35 alpha pod-restart subresource; the pod itself is preserved. Returns an empty 204 response on success. Required: kubernete_id, namespace, name. The cluster must expose the pod-restart subresource (Kubernetes 1.35+ with the matching feature gate enabled).
- **List all Portainer namespace secrets** (List). Get a Kubernetes Secret by name within a specified namespace in a Portainer environment. Returns the secret object including its name, namespace, and data. Required: kubernete_id, namespace, secret.
- **List all Portainer namespace service accounts** (List). Get a specific Kubernetes service account by name within a namespace in a Portainer environment. Returns: name. Required: kubernete_id, namespace, name.
- **Portainer service account image pull secrets bulk update** (Update). Replace the imagePullSecrets list on a Kubernetes service account in a Portainer environment with the provided list. Returns an empty 204 response on success. Required: kubernete_id, namespace, id.
- **List all Portainer namespace services** (List). List Kubernetes services for a given namespace in a Portainer environment. Returns: attributes containing Kubernetes service information as defined by the upstream K8sServiceInfo schema. Required: kubernete_id, namespace.
- **Create a Portainer namespace service** (Create). Create a Kubernetes service within a given namespace in a Portainer environment. Returns an empty 204 response on success. Required: kubernete_id, namespace.
- ...and 206 more tools. Call `tools/list` via the MCP endpoint, or see the full catalog via the API, for the complete set.
