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.Documentation Index
Fetch the complete documentation index at: https://developer.upsun.com/llms.txt
Use this file to discover all available pages before exploring further.

Key capabilities
| Capability | Description | Use case |
|---|---|---|
| Natural Language Infrastructure Management | Converts 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 Integration | Integrates 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 Automation | Supports 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: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.
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:Install in Cursor
Install in Cursor
Settings -> Cursor Settings -> MCP -> Add new global MCP serverCopying the following configuration into your Cursor ~/.cursor/mcp.json file is the recommended approach. You may also install in a specific project by creating .cursor/mcp.json in your project folder.See the Cursor MCP docs for more info.Cursor Remote Server Connection
Install in Claude Code
Install in Claude Code
Install in Windsurf
Install in Windsurf
Windsurf Remote Server Connection
Install in VS Code
Install in VS Code
VS Code Remote Server Connection
Install in Cline
Install in Cline
- Open Cline.
- Click the hamburger menu icon (☰) to enter the MCP Servers section.
- On the Remote Servers tab, click Edit Configuration.
- Add upsun to
mcpServers:
Install in Zed
Install in Zed
settings.json. See Zed Context Server docs for more info.Install in Augment Code
Install in Augment Code
- Press Cmd/Ctrl+Shift+P or go to the hamburger menu in the Augment panel.
- Select Edit Settings
- Under Advanced, click Edit in settings.json
- Add the server configuration to the
mcpServersarray in theaugment.advancedobject
Install in Roo Code
Install in Roo Code
Roo Code Remote Server Connection
Install in Gemini CLI
Install in Gemini CLI
- Open the Gemini CLI settings file. The location is
~/.gemini/settings.json(where~is your home directory). - Add the following to the
mcpServersobject in yoursettings.jsonfile:
mcpServers object does not exist, create it.Install in Claude Desktop
Install in Claude Desktop
Remote Server Connection
Open Claude Desktop and navigate to Settings > Connectors > Add Custom Connector. Enter the name asUpsun and the remote MCP server URL as https://mcp.upsun.com/mcp.Add your API token in the headers configuration:Install in Opencode
Install in Opencode
Opencode Remote Server Connection
Install in JetBrains AI Assistant
Install in JetBrains AI Assistant
- In JetBrains IDEs, go to
Settings->Tools->AI Assistant->Model Context Protocol (MCP) - Click
+ Add. - Click
Commandin the top-left corner of the dialog and select As JSON from the list. - Add this configuration and click
OK
- Click
Applyto save changes. - Repeat these steps to add
upsunfor JetBrains Junie: Go toSettings->Tools->Junie->MCP Settings.
Install in Kiro
Install in Kiro
- Navigate
Kiro>MCP Servers - Add a new MCP server by clicking the
+ Addbutton. - Paste the configuration given below:
- Click
Saveto apply the changes.
Install in Trae
Install in Trae
Trae Remote Server Connection
Install in Amazon Q Developer CLI
Install in Amazon Q Developer CLI
Install in Warp
Install in Warp
- Navigate
Settings>AI>Manage MCP servers. - Add a new MCP server by clicking the
+ Addbutton. - Paste the configuration given below:
- Click
Saveto apply the changes.
Install in Copilot Coding Agent
Install in Copilot Coding Agent
mcp section of your Copilot Coding Agent configuration file Repository->Settings->Copilot->Coding agent->MCP configuration:Install in LM Studio
Install in LM Studio
Manual set-up:
- Navigate to
Program(right side) >Install>Edit mcp.json. - Paste the configuration given below:
- Click
Saveto apply the changes. - Toggle the MCP server on/off from the right hand side, under
Program, or by clicking the plug icon at the bottom of the chat box.
Install in Visual Studio 2022
Install in Visual Studio 2022
Install in Crush
Install in Crush
Crush Remote Server Connection (HTTP)
Install in BoltAI
Install in BoltAI
Install in Rovo Dev CLI
Install in Rovo Dev CLI
Remote Server Connection
Install in Zencoder
Install in Zencoder
- Go to the Zencoder menu (…)
- From the dropdown menu, select Agent tools
- Click on the Add custom MCP
- Add the name and server configuration from below, and make sure to hit the Install button
Install in Qodo Gen
Install in Qodo Gen
- Open Qodo Gen chat panel in VSCode or IntelliJ.
- Click Connect more tools.
- Click + Add new MCP.
- Add the following configuration:
Qodo Gen Remote Server Connection
Install in Perplexity Desktop
Install in Perplexity Desktop
- Navigate to
Perplexity>Settings. - Select
Connectors. - Click
Add Connector. - Select
Advanced. - Enter Server Name:
Upsun - Paste the following JSON in the text area:
- Click
Save.
Related content
Upsun AI tutorials
- Upsun AI and Machine Learning tutorials
- Experiment with Chainlit AI interface with RAG on Upsun
- Access Upsun Documentation contextually via Context7 + MCP
- Use the Upsun API to automate Agent deployment
- Upsun MCP Server Announcement
Upsun AI documentation
- Host AI Agents on Upsun
- Deploy AI on Upsun