Skip to main content
The Model Context Protocol (MCP) lets AI clients like Claude Desktop and Cursor talk to your Datum Cloud resources directly, outside the terminal. This page covers the Datum MCP server. For the hosted Datum Docs MCP server, see Datum Docs MCP. Where the AI assistant is the interactive, terminal-first experience in datumctl, the Datum MCP server is the bridge that gives a desktop AI assistant secure, standards-based access to your organizations, projects, domains, proxies, DNS, and more.
The Datum MCP server is distributed as a separate datum-mcp binary, not as a datumctl subcommand. Installation, the full tool catalog, and one-click setup for clients such as Cursor live on the dedicated Datum MCP page and upstream in the Datum MCP repository.

When to use the MCP server

Reach for the MCP server when you want an AI client that lives outside your terminal to work with Datum Cloud:
  • Claude Desktop — chat with an assistant that can read and change your Datum resources.
  • Cursor and other IDE-embedded assistants — bring Datum context into your editor while you build.
  • Claude Code — install the datum-cloud plugin, which starts the server for you. See Add it to your AI client.
  • Any other MCP-aware client. Datum MCP speaks the standard stdio transport, and can also serve streamable HTTP.
If you would rather stay in the terminal, datumctl assistant answers questions in natural language without a separate MCP client — see the AI assistant guide.

What it exposes

The Datum MCP server gives connected clients tools to inspect and manage your Datum Cloud resources. Clients can understand the current state of your resources, suggest and implement changes, and help diagnose common configuration issues. The catalog covers:
  • Organizations, projects, and users
  • Domains, load balancers (HTTP proxies, routes, and gateways), and traffic protection
  • DNS zones and records
  • gVPC networks and network services
  • Compute workloads and Instances
  • IP address management, IAM, billing, and services
  • Activity search
  • Any other Datum resource, through a generic escape hatch
For load balancers, networks, Compute, DNS, and activity, the server also includes each service’s own diagnostic tools, the same ones Datum’s AI assistant uses. To keep the tool list short, the server loads some toolsets on demand during a session.
The tool catalog evolves with the server. See the Datum MCP page for the authoritative, up-to-date list and the exact operations each tool supports.

Connecting a client

Most MCP clients launch the server over stdio. Add an entry like this to your client’s MCP configuration:
1

Install the Datum MCP server

Follow the install instructions on the Datum MCP page. Binaries are available for Linux, macOS, and Windows on x86 and arm64.
2

Add the server to your client

In Claude Code, install the datum-cloud plugin from the datum-cloud/claude-code-plugins marketplace, which starts the server for you. For other clients, point them at the datum-mcp binary using a stdio configuration like the one above. Cursor users can use the one-click install link on the Datum MCP page.
3

Sign in on first use

The first tool call triggers a browser-based sign-in (see below). Approve it, and your client is connected.

Authentication

On first use, the server runs a browser-based OAuth (PKCE) sign-in, then stores credentials — including a refresh token — securely in the system keychain. Subsequent calls reuse and refresh the token automatically, so you sign in once. This is the same security model datumctl uses when you log in: no static API keys. To run Datum MCP without a browser, such as in CI or on a server, set DATUM_TOKEN and DATUM_API_HOSTNAME instead. With a service account token, the server works in that service account’s own project. The server implements the latest MCP Authorization specification and supports OAuth 2.1 (PKCE).
The MCP server acts on real Datum Cloud resources with your credentials. Connect it only to AI clients you trust, and review any changes an assistant proposes before approving them.

Next steps

  • Datum MCP — set up the Datum MCP server: install, one-click client setup, and the full tool catalog.
  • Datum Docs MCP — give your AI client the docs as well, with no installation.
  • AI assistant — prefer the terminal? Use datumctl assistant instead.
  • Logging in — review how Datum Cloud handles credentials before your first connection.
Last modified on October 29, 2026