
DigitalOcean MCP Server
A server that exposes DigitalOcean App Platform functionality through standardized tools, enabling AI assistants to directly manage your DigitalOcean apps without writing code or memorizing API endpoints.
README
DigitalOcean MCP Server
This MCP server exposes DigitalOcean App Platform functionality through standardized tools that can be used by any MCP client, including Claude Desktop and Cursor. It enables AI assistants to directly manage your DigitalOcean apps without writing code or memorizing API endpoints.
📚 Table of Contents
🚀 What Can You Do With It?
You can now do things like:
- Deploy a new app from a GitHub repo
- Quickly redeploy an existing app with the latest changes
- See logs, restart components, or delete old environments
- Check available regions and create apps based on what’s supported
- Build and deploy an app from scratch, entirely through your assistant
...and more!
🧰 Prerequisites
To use the DigitalOcean MCP Server, you’ll need:
- Node.js (≥ 12) & npm
- A DigitalOcean Personal Access Token with App Platform scopes
- A supported MCP client:
- Claude Desktop (v1.9+)
- Claude Code
- Cursor
- Windsurf
- (Optional but helpful): GitHub CLI (gh) - useful for cloning repos, creating projects, and working with GitHub-based apps.
💡 You do not need to install anything—this server runs via npx, with just a one-line config added to your MCP client.
⚙️ Setting up your DigitalOcean MCP Server
1. Generate Your API Token
Head to DigitalOcean’s API settings and create a new Personal Access Token with App Platform permissions.
2. Add the Server to Your MCP Client
Add this JSON snippet to your client’s MCP config file:
{
"mcpServers": {
"digitalocean": {
"command": "npx",
"args": ["@digitalocean/mcp"],
"env": {
"DIGITALOCEAN_API_TOKEN": "YOUR_DO_TOKEN"
}
}
}
}
Here’s what each part of the snippet does:
-
- command: how to launch the server (
npx
or full path)
- command: how to launch the server (
-
- args: the package name
-
- env: insert your DO token here
Then follow the instructions for your specific tool:
Claude Desktop
- Go to Settings → Developer → Edit Config
- Add the snippet above to
claude_desktop_config.json
- Replace
YOUR_DO_TOKEN
with your token - Save and restart Claude Desktop
- You'll see “digitalocean” listed as an available server
Setting up DigitalOcean MCP Server in Claude Desktop
Cursor
- Go to Settings → Cursor Settings → MCP → Add a new global MCP server
- Cursor will open
~/.cursor/mcp.json
- Add the snippet above to this json file
- Replace
YOUR_DO_TOKEN
with your token - Save, and return to MCP Settings.
- You should now see “digitalocean” in Cursor’s MCP settings
Setting up DigitalOcean MCP Server in Cursor
Windsurf Setup
- In Windsurf: Settings → Windsurf Settings → Cascade → MCP → Add Server → Add custom server
- Windsurf will open
~/.codeium/windsurf/mcp_config.json
- Add the snippet above to this json file
- Replace
YOUR_DO_TOKEN
with your token - Save, and return to MCP Settings.
- You should now see “digitalocean” in Windsurf's MCP settings
Setting up DigitalOcean MCP Server in Windsurf
💬 Example Prompts
Once it’s configured, try asking your assistant:
“List all active apps on my account”
“Create a new app from https://github.com/do-community/do-one-click-deploy-flask with 1GB RAM in NYC3”
“Show logs for checkout-service”
“Cancel the current deployment for marketing-site”
“Delete the old `staging-env` app”
The assistant will send the request → the MCP server talks to DigitalOcean → you get structured results, ready to act on.
Available Tools
Category | Commands |
---|---|
Apps | list_apps , create_app , get_app , update_app , delete_app , restart_app |
Deployments | list_deployments , create_deployment , get_deployment , cancel_deployment |
Logs | retrieve_active_deployment_logs , download_logs |
Infra | list_app_regions , list_instance_sizes |
Alerts | list_app_alerts , update_app_alert_destinations |
Rollbacks | validate_app_rollback , rollback_app , commit_app_rollback , revert_app_rollback |
Metrics | get_app_bandwidth_daily_metrics , get_all_app_bandwidth_daily_metrics |
Validation | validate_app_spec |
Troubleshooting
The server doesn’t appear in your client?
- Make sure your JSON config is saved and valid
- Restart your MCP client (Claude, Cursor, Windsurf)
Token not working?
- Check that it has App Platform access
- Try generating a fresh one
JSON errors?
- No trailing commas
- No comments allowed in JSON
You can also test the server directly by running:
npx @digitalocean/mcp
Contributing
We’d love your help improving this! Bug reports, new features, and docs improvements are all welcome.
- Fork this repo
- Create a branch (
git checkout -b feature/awesome-tool
) - Open a PR
License
This project is licensed under the MIT License.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.