Skip to content
DigitalOcean

DigitalOceanMCP Server

Added to Onei
v1.0.67
MIT

Summary

DigitalOcean's official MCP server — deploy apps and manage Droplets, databases, and storage conversationally.

Features

  • Deploy and manage App Platform applications
  • Provision Droplets, databases, and Spaces
  • Read deployment logs and app configuration

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

  1. Open your agent's MCP configuration file.
  2. Merge the snippet below into it, filling in the environment variables with your own values.
  3. Restart the agent — the "DigitalOcean" tools will be available.
{
  "mcpServers": {
    "digitalocean": {
      "command": "npx",
      "args": [
        "-y",
        "@digitalocean/mcp"
      ],
      "env": {
        "DIGITALOCEAN_API_TOKEN": "your-token"
      }
    }
  }
}

Description

DigitalOcean's official MCP server gives an assistant control of a DigitalOcean account, with App Platform as the most useful surface.

What it covers
  • App Platform — create, deploy, and manage applications, read build and runtime logs, and update configuration. Deploying from a repository becomes a request rather than a console session.
  • Droplets — create, resize, snapshot, and destroy virtual machines
  • Managed databases — provision and configure Postgres, MySQL, Redis, and MongoDB instances
  • Spaces object storage
  • Networking — floating IPs, firewalls, and load balancers
  • Kubernetes cluster management
Why App Platform in particular

The deploy-check-logs-fix loop is where an assistant adds most value, because reading a failed build log and identifying the cause is exactly what it is good at. Having deploy and logs in the same interface as the code makes that loop tight.

Setup

Requires a DigitalOcean API token; runs with npx @digitalocean/mcp. Scope the token to read-only unless you specifically want provisioning, since creating resources costs money.

Related MCP Servers

MCP: AWS MCP Server

by Amazon Web Services

Featured

AWS's managed MCP server: call any AWS API, run sandboxed Python against your account, and load AWS agent skills on demand — under IAM, CloudWatch and CloudTrail.

Featured

Google's official MCP server for driving the gcloud CLI from natural language, with allowlist and denylist controls over which commands an agent may run.

Browse all MCP servers →