zopnight

ZopNight provides a Model Context Protocol (MCP) server that lets AI assistants query your cloud infrastructure data directly. You can ask your AI tool about resources, costs, schedules, recommendations, and more — all through natural language.

[!note] Note What is MCP?

MCP (Model Context Protocol) is an open standard that allows AI tools to connect to external data sources. ZopNight's MCP server uses Streamable HTTP transport — your AI tool sends standard HTTP POST requests to the server. It is not WebSocket based, and there is no STDIO option: this is a remote server, not a local process.

Prerequisites

Before connecting, you need:

• A ZopNight account with at least one organisation
• Admin or Editor role in the organisation
• MCP Server enabled for your organisation
• Either an OAuth-capable MCP client (Cursor, Claude Desktop, Claude Code, ChatGPT, VS Code, Codex, and 13 more) or a Personal Access Token for CI, scripts, or non-browser clients

Follow the How to Connect guide for the protocol-level details of both auth flows.

How It Works

1. Your AI tool sends a POST request to the MCP server URL with a Bearer token — either an OAuth 2.1 access token or a Personal Access Token
2. The gateway validates the token and resolves your identity from it
3. The AI tool calls list_organisations to discover your organisations
4. The server checks that MCP is enabled for the requested organisation
5. The server verifies you are a member of that organisation
6. The gateway checks the call against your live role — and, if the tool changes something, against the organisation's Write access setting and the token's granted scopes
7. Results are returned as JSON to the AI tool

Every check happens at the gateway, on the way in, against the same policy table the UI's own calls resolve against. MCP is not a second way in with rules of its own, and because your role is read per request, revoking access in the app takes effect on the agent's next tool call. OAuth access tokens are short-lived and refresh-token rotation with reuse detection means a leaked refresh token kills the whole family on next use.

[!note] Note Protocol Details

The MCP server speaks JSON-RPC 2.0 over HTTP POST. It supports initialize, tools/list, tools/call and notifications/*, and it answers ping on the protocol revisions in use today. Anything else answers -32601 method not found, which is correct rather than missing — a server must not advertise a capability it has not implemented. One method moves between revisions: the 2026-07-28 revision removes ping and adds server/discover, so a client that negotiates that revision gets -32601 for ping.

Your client picks the response format with its Accept header. application/json (or no Accept) returns one buffered JSON response, which is what most clients do. A client that sends text/event-stream gets the reply as Server-Sent Events instead, which is what lets a long-running tool report progress while it works. Both are Streamable HTTP; neither is WebSocket.

Set up your client

Developer docs cover the protocol, auth flow, and tool catalogue — what the server implements and how a client talks to it. Product docs cover the per-client setup (one-click install links, config-file paste snippets, screenshots) for the 19 supported clients.

• ZopNight: zop.dev/docs/zopnight/integrations/mcp
• ZopDay: zop.dev/docs/zopday/integrations/mcp

If your client speaks OAuth 2.1, point it at the public MCP URL and it will discover the authorization server on its own — see How to Connect for the discovery endpoints it uses.

What Can You Do?

The MCP server exposes read tools covering resources, costs, schedules, recommendations, cloud accounts, teams, budgets, metrics, billing, and audit logs, plus write tools that change things. See Available Tools for the categorical breakdown and the current inventory. Your own list is filtered to what your token, role, and organisation Write access allow — ask your AI tool to list its ZopNight tools for the authoritative view.

[!note] Note Write access is one setting per organisation

How much an agent may change is set per organisation, via Write access in Settings → Organisation, with four cumulative levels from read-only through to irreversible changes. An agent can never exceed the permissions of the person whose token it holds, nor the OAuth scopes (or PAT capabilities) the token was granted.

Before you raise that setting, read the disclosure in How to Connect: enabling MCP write means any content in your cloud environment becomes a potential instruction to your agent.

Having issues? See the Troubleshooting guide for common problems and solutions.