mcp-server-digitalocean
This server allows you to manage DigitalOcean cloud infrastructure through an AI assistant, covering the following capabilities:
Droplets: List, get details, create (specifying name, region, size, image, SSH keys, and tags), and delete virtual servers.
Databases: List and get details about managed database clusters.
Domains: List, create (with an associated IP/A record), and delete domains.
Infrastructure: Browse available datacenter regions and Droplet sizes with pricing and capability details.
Account: View your DigitalOcean account information, email, UUID, and usage limits.
Manages DigitalOcean cloud resources, including account info, Droplets (list, get, create, delete), managed databases, domains, regions, and sizes.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-server-digitalocean List all my Droplets"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
DigitalOcean MCP Server
A Model Context Protocol server for DigitalOcean cloud infrastructure. Manage Droplets, databases, domains, and more — all through your AI assistant.
What Can You Do With It?
Manage Droplets — list, create, get details, and delete Droplets
Query Databases — list and inspect managed database clusters
Handle Domains — list, create, and delete domain records
Explore Infrastructure — browse available regions and Droplet sizes with pricing
Check Account — view account info and usage limits
Related MCP server: timeweb-mcp-server
Table of Contents
Prerequisites
Python >= 3.10
A supported MCP client:
Installation
Using uv (recommended)
uv tool install mcp-server-digitaloceanUsing pip
pip install mcp-server-digitaloceanSetup
1. Generate Your API Token
Go to DigitalOcean API Tokens and create a new Personal Access Token.
2. Add the Server to Your MCP Client
Add this JSON snippet to your client's MCP config file:
{
"mcpServers": {
"digitalocean": {
"command": "uvx",
"args": ["mcp-server-digitalocean"],
"env": {
"DIGITALOCEAN_TOKEN": "YOUR_DO_TOKEN"
}
}
}
}Then follow the instructions for your specific client:
Claude Desktop
Go to Settings > Developer > Edit Config
Add the snippet above to
claude_desktop_config.jsonReplace
YOUR_DO_TOKENwith your tokenSave and restart Claude Desktop
You'll see "digitalocean" listed as an available server
Cursor
Go to Settings > Cursor Settings > MCP > Add a new global MCP server
Cursor will open
~/.cursor/mcp.jsonAdd the snippet above to this JSON file
Replace
YOUR_DO_TOKENwith your tokenSave and return to MCP Settings
Windsurf
Go to Settings > Windsurf Settings > Cascade > MCP > Add Server > Add custom server
Windsurf will open
~/.codeium/windsurf/mcp_config.jsonAdd the snippet above to this JSON file
Replace
YOUR_DO_TOKENwith your tokenSave and return to MCP Settings
Claude Code
Run in your terminal:
claude mcp add digitalocean -- uvx mcp-server-digitaloceanSet the environment variable:
export DIGITALOCEAN_TOKEN="your-token-here"Available Tools
Category | Tools |
Account |
|
Droplets |
|
Databases |
|
Domains |
|
Infrastructure |
|
Example Prompts
Once configured, try asking your assistant:
"List all my Droplets"
"Create a new 1GB Droplet in NYC1 running Ubuntu 24.04"
"Show me all available regions"
"List my database clusters"
"Delete droplet 42"
"What Droplet sizes are available and how much do they cost?"Development
# Clone the repo
git clone https://github.com/truecallerabreham/mcp-server-digitalocean.git
cd mcp-server-digitalocean
# Install dependencies
uv sync
# Run tests
uv run pytest
# Run linter
uv run ruff check src/ tests/
# Type check
uv run pyrightTroubleshooting
The server doesn't appear in your client?
Make sure your JSON config is saved and valid (no trailing commas)
Restart your MCP client (Claude, Cursor, Windsurf)
Check that
uvxis in your PATH
Token not working?
Verify the token has the correct scopes
Try generating a fresh one at DigitalOcean API Tokens
Still having issues?
Test the server directly:
DIGITALOCEAN_TOKEN="your-token" uvx mcp-server-digitaloceanContributing
Contributions are welcome! Bug reports, new features, and docs improvements are all appreciated.
Fork this repo
Create a branch (
git checkout -b feature/my-feature)Make your changes
Run tests (
uv run pytest)Open a PR
License
This project is licensed under the MIT License.
Available Tools
12 toolscreate_domainBIdempotent
Create a new domain in your account.
Inputs: name (required), ip_address (required).
create_dropletB
Create a new Droplet. Specify name, region, size, and image.
Inputs: name (required), size (required), image (required), region (required), +2 more.
delete_domainBDestructiveIdempotent
Delete a domain from your account.
Inputs: name (required).
delete_dropletADestructiveIdempotent
Permanently delete a Droplet. This action is irreversible.
Inputs: droplet_id (required).
get_accountARead-onlyIdempotent
Get your DigitalOcean account information including email, UUID, and account limits.
Inputs: no named parameters.
get_databaseARead-onlyIdempotent
Get detailed information about a specific database cluster.
Inputs: database_id (required).
get_dropletARead-onlyIdempotent
Get detailed information about a specific Droplet by its ID.
Inputs: droplet_id (required).
list_databasesARead-onlyIdempotent
List all database clusters in your account.
Inputs: no named parameters.
list_domainsARead-onlyIdempotent
List all domains in your account.
Inputs: no named parameters.
list_dropletsARead-onlyIdempotent
List all Droplets in your account. Returns droplet IDs, names, statuses, IPs, regions, and sizes.
Inputs: page, per_page.
list_regionsARead-onlyIdempotent
List all available DigitalOcean datacenter regions.
Inputs: no named parameters.
list_sizesARead-onlyIdempotent
List all available Droplet sizes with pricing and capability info.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 12 tools
Each tool targets a distinct resource and action: create, delete, get, list for droplets and domains; get/list for databases; list for regions and sizes; and get_account for account info. No overlap.
All tools follow a consistent verb_noun pattern in snake_case (e.g., create_droplet, list_domains). No mixing of conventions.
12 tools is well-scoped for a DigitalOcean API server, covering key resources without being excessive or too few.
Basic CRUD for droplets and domains is covered, but missing update operations, database creation/deletion, and droplet actions (e.g., power on/off). Notable gaps exist.
Maintenance
Related MCP Connectors
Manage American Cloud VMs, Kubernetes, databases, storage, networks and DNS from your AI assistant.
Query, explore, and manage your databases through natural conversation.
Interact with the Stitch API using natural language commands.
Deploy, monitor, and manage your OpenClaw AI assistants via natural language.
Related MCP Servers
- FlicenseBqualityNot gradedmaintenanceProvides comprehensive access to 471+ DigitalOcean API endpoints, enabling AI assistants to manage cloud infrastructure including droplets, databases, load balancers, DNS, Kubernetes, and other DigitalOcean resources programmatically.6-
- AlicenseBqualityDmaintenanceEnables management of Timeweb Cloud resources including servers, databases, Kubernetes clusters, S3 storage, DNS, SSH keys, and floating IPs through natural language.9711 npmMIT
- AlicenseCqualityBmaintenanceEnables deploying applications and managing cloud resources in Timeweb Cloud through natural language.245165 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables managing Sliplane deployments, projects, and application status through natural language, with OAuth or API key auth.MIT