# mctl-api MCP server

> Provides a dual-protocol gateway to manage services, workspaces, databases, and platform operations via REST and MCP.

- Repository: https://github.com/mctlhq/mctl-api
- Page: https://hostedmcp.org/servers/mctlhq/mctl-api
- Transport: —
- Stars: 0
- License: Apache-2.0

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `MCTL_API_TOKEN` | no | no |  |
| `MCTL_API_URL` | no | no |  |

## Tools (12)

- `mctl_list_tenants`
- `mctl_list_services`
- `mctl_get_tenant`
- `mctl_get_service_status`
- `mctl_get_service_config`
- `mctl_get_resource_usage`
- `mctl_get_service_logs`
- `mctl_deploy_service`
- `mctl_create_tenant`
- `mctl_provision_database`
- `mctl_rollback_service`
- `mctl_retire_service`

## FAQ

### What protocols does mctl-api support?

It supports both REST endpoints and the Model Context Protocol (MCP) for dual-protocol access.

### How are write operations executed in the platform?

All write operations are performed through Argo Workflows and reconciled by ArgoCD using a GitOps repository.

### Which AI clients can connect to this server?

AI coding assistants such as Claude, Copilot, Cursor, Gemini, and others can connect via the MCP protocol.

### Does the server support authentication?

Yes, it uses OAuth 2.1 with PKCE via ZITADEL, federated OIDC JWTs, and static service tokens.
