> For the complete documentation index, see [llms.txt](https://docs.ai.neevcloud.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ai.neevcloud.com/getting-started/mcp/overview.md).

# Overview

### What is Model Context Protocol (MCP)?

Model Context Protocol (MCP) is an open standard that enables AI assistants to securely interact with external tools, services, and data sources through a consistent interface. Instead of manually switching between applications or copying information, MCP allows AI clients to communicate directly with supported servers to perform tasks on your behalf.

With NeevCloud MCP, AI assistants can access NeevCloud services directly, allowing you to interact with cloud resources using natural language.

![NeevCloud MCP Overview](https://1980728309-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FSqquJG2zKVZ5l1Sd5aQy%2Fuploads%2Fgit-blob-47fdcd4cf3aaa4be8c5d4abb470e129a9f8a1952%2Fmcp-overview.jpg?alt=media)

***

### Why Use NeevCloud MCP?

NeevCloud MCP enables AI assistants such as Claude Desktop, Cursor, and Codex to communicate directly with the NeevCloud Console.

Once connected, you can perform common cloud operations without leaving your AI assistant, making development workflows faster and more efficient.

Some examples include:

* Creating, listing, and deleting AI runtimes, and checking their metrics
* Viewing available GPU resources and configurations
* Browsing plans, products, and the models available through the Model API
* Looking up your organizations and projects

**Want your agent to work inside a sandbox instead?** That is a separate server built for it: the [Sandbox MCP Server](https://docs.ai.neevcloud.com/agentic-studio/overview/integrations-and-support/sandbox-mcp-server.md) gives an agent its own isolated Linux machine to run commands, edit files, and manage processes, with a project API key and no sign-in.

***

### Supported AI Clients

This guide covers connecting NeevCloud MCP with:

* Claude Desktop
* Cursor
* Codex (VS Code Extension)

***

### Prerequisites

Before connecting any AI client, make sure you have:

* A NeevCloud account
* Client like Claude Desktop, Cursor, VS Code with Cursor extension downloaded

Note: The process for generating a Personal Access Token (PAT) is the same for all supported AI clients.

***

### Generate a Personal Access Token (PAT)

1. Login into [NeevCloud Console](https://console.ai.neevcloud.com/).
2. Navigate to Accounts → Access Tokens.
3. Click Create Token.
4. Enter a token name and select an expiration period.
5. Click Create.
6. Copy the generated PAT and store it securely.

You'll use this token while configuring NeevCloud MCP in Claude Desktop, Cursor, or Codex.

***

### Next Steps

Choose your preferred AI client:

* If you're using Claude Desktop or Claude Code, see the [Connect Claude Desktop](https://docs.ai.neevcloud.com/getting-started/mcp/connect-claude-desktop.md) guide.
* If you're using Cursor, see the [Connect Cursor](https://docs.ai.neevcloud.com/getting-started/mcp/connect-cursor.md) guide.
* If you're using Codex, see the [Connect Codex](https://docs.ai.neevcloud.com/getting-started/mcp/connect-codex.md) guide.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.ai.neevcloud.com/getting-started/mcp/overview.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
