# Now Available: Remote MCP for DigitalOcean Services

DevFeed: [Now Available: Remote MCP for DigitalOcean Services](<https://devfeed.tech/articles/now-available-remote-mcp-for-digitalocean-services-19937.md>)

Original publisher: [Read original article](<https://www.digitalocean.com/blog/remote-mcp-server>)

Author: Dinesh Murthy

Published: 2025-12-09T18:53:48Z

Content type: release

Language: en

Sources: [DigitalOcean](<https://devfeed.tech/sources/digitalocean.md>)

Topics: [Digital Ocean](<https://devfeed.tech/topics/digital-ocean.md>), [MCP Server](<https://devfeed.tech/topics/mcp-server.md>), [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [cloud-infrastructure](<https://devfeed.tech/topics/cloud-infrastructure.md>)

Tags: [ai-ml](<https://devfeed.tech/tags/ai-ml.md>), [api](<https://devfeed.tech/tags/api.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [developers](<https://devfeed.tech/tags/developers.md>), [digitalocean](<https://devfeed.tech/tags/digitalocean.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-server](<https://devfeed.tech/tags/mcp-server.md>), [remote-mcp-server](<https://devfeed.tech/tags/remote-mcp-server.md>)

## AI overview

DigitalOcean now supports Remote MCP Server for select services, allowing developers to connect AI tools to hosted MCP endpoints without installing local binaries. The release provides dedicated HTTPS endpoints for nine services and uses authenticated access with a DigitalOcean API token.

## Source excerpt

Earlier this year, DigitalOcean introduced the DigitalOcean Model Context Protocol (MCP) Server, allowing developers to connect applications and AI-assistants like Cursor and Claude Desktop directly to their DigitalOcean cloud infrastructure. You could ask your AI assistant to deploy apps, check database status, or troubleshoot droplet issues - all conversationally, making your infrastructure "AI-readable". Until now, this required running the MCP server locally using the npx binary on your computer. Remote MCP support is now available on DigitalOcean. You can now connect your AI tools to DigitalOcean services without installing any binaries locally. Remote MCP endpoints are live for 9 DigitalOcean services: Accounts, App Platform, Databases, DigitalOcean Kubernetes, Droplets, Insights, Marketplace, Networking, and Spaces. Each service runs as its own MCP server at a dedicated HTTPS endpoint (example: https://apps.mcp.digitalocean.com/mcp for App Platform). Just update your MCP client configuration to point at our hosted endpoints, include your DigitalOcean API token and you're ready to go with immediate, authenticated access to your infrastructure. All existing DigitalOcean MCP tutorials and videos continue to work. The only change is your mcp.json configuration. Why Remote MCP? MCP is an open standard for connecting AI tools to external systems and data sources. It provides a consistent interface for exposing tools and context to LLMs. While Local MCP servers work great, Remote MCP now gives you a zero-setup production-ready experience, with the following advantages: No local dependencies: Skip the Docker installs, Go binaries, and background processes. Modular connections: Connect only to the services you need (e.g. just Databases, just Kubernetes, or any combination) by picking specific MCP endpoints. Always up to date: We handle server versioning and rollouts, so your application always has access to the latest DigitalOcean API features and tools. Standardizati