Skip to main content
The Upsun Model Context Protocol (MCP) Server enables management of Upsun projects and environments through AI assistants such as Claude. It supports conversational commands to create, modify, and monitor infrastructure without using the terminal or console. MCP projects

Key capabilities

CapabilityDescriptionUse case
Natural Language Infrastructure ManagementConverts user instructions written in natural language to corresponding API operations.- “Show me all active environments in my project.”
- “Add Redis caching to my staging environment.”
CI/CD IntegrationIntegrates with existing development workflows and interacts with CI/CD pipelines to trigger or respond to automated workflows.- Trigger deployments from the IDE.
- Monitor build progress from documentation tools or chat interfaces.
AI-Based AutomationSupports AI-driven automation that adapts to real-world conditions by analyzing metrics, historical data, and usage patterns.- Resource allocation based on usage trends.
- Automated troubleshooting with suggested root causes.
- Adaptive backup scheduling.

Security Model

All MCP operations follow the existing Upsun security model. The MCP Server defaults to read-only operations for safety, with write operations available through explicit configuration. To enable write operations, include the following header in your MCP configuration:
{
  "enable-write": "true"
}

Security Implications

Enable write operations only if you understand the associated security implications and trust your AI assistant to modify infrastructure resources.

Architecture

The Upsun MCP Server uses Streamable HTTP transport for communication and event streaming. It uses HTTP POST for client-to-server messages with optional Server-Sent Events for streaming capabilities. This transport enables remote server communication and supports standard HTTP authentication methods including bearer tokens, API keys, and custom headers. MCP Architecture

Installation

1. Generate an API Token

  • In the Upsun Console, open your account settings.
  • Generate a new API token with permissions appropriate for your projects.

2. Configure the MCP Client

  • Configure your MCP client to connect to mcp.upsun.com/mcp.

3. Connect and Use

  • Connect your AI assistant or any MCP-compatible client.
  • Begin managing Upsun resources using natural language commands.

Select your preferred client

The Upsun MCP server works with all major AI development environments.
Choose your preferred client from the list below:

Upsun AI tutorials

Upsun AI documentation

Last modified on March 11, 2026