Model Context Protocol (MCP)

Built in: Connect coding agents directly to ZenSailor over authenticated Streamable HTTP.

An MCP server is a lightweight program that implements the Model Context Protocol (MCP), enabling AI agents to securely interact with external systems like APIs, databases, or infrastructure tools.

ZenSailor exposes a secure MCP endpoint that allows you to control your PaaS using natural language from tools like Cursor, Windsurf, or Claude Desktop.

Features

  • List Services:Ask your AI “What services are running?” or “Show me failed deployments”.
  • Restart Services:Command “Restart the Traefik router” or “Redeploy the payment service”.
  • Documentation: Your AI can read the full ZenSailor docs to answer your questions accurately.

Agent Skill & Persistent Storage

ZenSailor ships a ready-to-paste Agent Skill — a formal SKILL.md that teaches compatible agents how to operate your PaaS: every MCP tool, the REST API syntax, permissions, and step-by-step workflows. Download it from API Documentation → Download Agent Skill inside your instance. Install it as .codex/skills/zensailor/SKILL.md, or reuse its instructions in AGENTS.mdor your editor’s rules file.

The skill also teaches the one rule agents must know when writing compose files: use the ${ZENSAILOR_DATA_PATH} variable for persistent volumes. ZenSailor builds in a temporary folder, so relative paths like ./dataare wiped on every redeploy. The variable resolves to the service’s permanent directory (/opt/zensailor/volumes/<project>/<service>) and is also available inside the container as an environment variable.

YAML
# docker-compose.yml — persistent volumes
volumes:
  - ${ZENSAILOR_DATA_PATH}/pgdata:/var/lib/postgresql/data

Configuration

Connect your favorite AI code editor or agent using the configuration below. ZenSailor authenticates every request, binds each session to its API key, and applies the key owner’s organization permissions to every tool.

Generate an API token inside your instance at Settings > Security.

JSON Config
{
  "mcpServers": {
    "zensailor": {
      "type": "http",
      "url": "https://paas.example.com/api/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Direct Streamable HTTP connection. Add this to .cursor/mcp.json or your editor's MCP configuration.

Review agent actions: Redeploy and proxy-restart tools are marked destructive so compatible clients can request confirmation before changing running infrastructure.