Nebius MCP Server
Enables AI agents to fetch Nebius cloud service documentation and execute Nebius CLI commands for managing cloud resources like compute instances and storage buckets through natural language interactions.
README
[Beta] Nebius MCP Server
This service allows AI agents and assistants to fetch documentation for the Nebius services and execute Nebius CLI commands through the Model Context Protocol.
Disclaimer
Important: This is a beta version. Use it carefully and at your own risk. There are no guarantees provided regarding stability, safety, or correctness.
In the current implementation, the MCP server allows execution of any Nebius CLI commands, which may lead to destructive and insecure consequences. Always double-check the command suggested by the assistant before executing it. Never use the Allow always option for the nebius_cli_execute tool.
Scenarios
There are 2 main scenarios for this MCP server:
-
Get and analyze the documentation for every service
Examples (queries to the AI agent):
- How to create a compute instance at Nebius?
- How to create a storage bucket at Nebius?
-
Execute commands and get results
Examples:
- Provide me a list of all storage buckets within the project: project-e00some-cool-project
- Get me a list of the available compute platforms
- Show the details about the compute instance by name: some-cool-instance
Requirements
- Python (version >=3.13) with uv package manager installed
- Nebius CLI (version >=0.12.65) installed locally with at least one profile configured
On macOS, it’s recommended to install uv via Homebrew: brew install uv.
Installation
Update to the latest version of Nebius CLI:
nebius update
Use the next command to configure your MCP-compatible client (see examples below):
uvx --refresh-package nebius-mcp-server "nebius-mcp-server@git+https://github.com/nebius/mcp-server@main"
Restricted actions and safe mode
For safety reasons Nebius MCP server always forbids execution of any commands that either accept tokens or access keys as an argument or return them as a result.
Safe mode: by default MCP server also does not allow to execute commands that can make "update", "delete" and other commands that can make potentially dangerous changes. We don't recommend changing the default behavior. However it can be controlled using the SAFE_MODE=true|false environment variable for the MCP server.
Using Claude Desktop
-
Install Claude Desktop: https://claude.ai/download
-
Open the Claude Desktop configuration file: Claude -> Settings -> Developer -> Edit Config
-
Edit the configuration file to include the Nebius MCP Server:
{ "mcpServers": { "Nebius MCP Server": { "command": "uvx", "args": [ "--refresh-package", "nebius-mcp-server", "nebius-mcp-server@git+https://github.com/nebius/mcp-server@main" ], "env": {} } } } -
Restart Claude Desktop:
- After restarting, click "Search and tools" icon in the bottom left corner of the input box
- You should see Nebius MCP Server is available for use
Using VSCode Copilot
-
Ensure you have the Copilot extension installed and are logged in
-
Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run mcp: Add Server
-
Choose
Command (stdio)and enter the following command:uvx --refresh-package nebius-mcp-server "nebius-mcp-server@git+https://github.com/nebius/mcp-server@main" -
Open the Chat panel and select Agent mode
- You will now see the new MCP and its available tools by clicking the :hammer_and_wrench: button
Tools
- nebius_profiles - Information about configured Nebius CLI profiles
- nebius_available_services - List of the available Nebius services
- nebius_cli_help - Detailed help documentation for the Nebius CLI commands for the specified service
- nebius_cli_execute - Generate and execute Nebius CLI command and return the result
Trademarks
"Model Context Protocol", "MCP", and the MCP logo are trademarks of Anthropic.
License
This project is licensed under the MIT License. See the LICENSE file for details.
Copyright (c) 2025 Nebius B.V.
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.
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.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.
E2B
Using MCP to run code via e2b.