• PROVISIONED
  • OPTIMIZED
  • MONITORED
  • HUMAN

How to deploy cloud resources with your AI

Connect your AI to the Akash Network to manage decentralized compute. Once connected, your agent handles the heavy lifting of finding and leasing hardware via SDL manifests.

Ask AI about this page

Short answer

How can I use my AI to deploy Akash cloud resources?

Your AI reads your SDL manifests and uses the Akash Network tools to find hardware bids and create deployments. You get a running cloud instance without manual CLI commands. This breakdown shows how your agent handles the lifecycle from bidding to leasing.

Deployment outcomes

What you get

The results of your AI's interaction with the network.

PROVISIONED

Active cloud instances

The AI completes the deployment process. You get a live environment running your specific workload.

OPTIMIZED

Best price hardware

Your agent compares different provider bids. You get the most cost-effective GPU or CPU for your needs.

MONITORED

Lease management

The AI manages the active lease. You can track what is running and how long it stays active.

HUMAN

Manual oversight

You decide when to approve a specific bid or terminate a lease. The AI won't spend your funds without your direction.

The workflow

What your AI does when the manifest arrives.

The AI translates your high-level intent into specific Akash Network API calls.

  1. Analyze requirements

    Your agent reads your SDL manifest to understand the CPU, GPU, and storage you need.

    create_deployment

  2. Find providers

    The AI scans the network to see which providers have matching hardware available.

    list_bids

  3. Select best bid

    Your agent compares the available bids to find the best fit for your constraints.

    list_bids

  4. Finalize hardware

    The AI secures the chosen hardware by initiating the lease process.

    create_lease

Try it

Copy these to start.

Use these prompts to kick off your deployment.

Starting points

Replace the bracketed text with your actual manifest file or specific hardware requirements.

Akash Network Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_EuiIRYnmcVok7TPlrVtxL0krEFU1GLjnS5iObiJa/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Akash Network capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "akash-network-decentralized-gpu-cloud-api-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_EuiIRYnmcVok7TPlrVtxL0krEFU1GLjnS5iObiJa/mcp"
    }
  }
}
Copy into chat04

  • Read my SDL manifest at [path/to/file] and list the available bids for this deployment.

  • Find the cheapest GPU bid that meets the requirements in my manifest.

  • Create a deployment using the best bid found for my AI workload.

  • Check the current active leases on the Akash Network.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Akash Network once, then ask.

One connection gives your AI client access to the entire Akash API. Your credentials stay encrypted and secure.

Connect Akash Network to your AI

FAQ

How this task behaves

  • 01

    Can my AI automatically spend my money on bids?

    No. The AI can find and suggest bids, but you must provide the final approval for any lease or deployment.

  • 02

    Does the AI manage my private keys?

    No. The AI uses the tools provided by the MCP to interact with the network, but it does not have access to your private keys.

  • 03

    Can the AI fix a failed deployment?

    The AI can list existing deployments and attempt to create new ones, but it cannot manually debug the internal state of a provider's hardware.

  • 04

    Can I use this to deploy to AWS or Google Cloud?

    No. This MCP is specifically for the Akash Network decentralized cloud.

  • 05

    Will the AI delete my existing deployments?

    No. There are no tools in this MCP that allow the AI to delete or destroy resources.

  • More questions about Akash Network? See everything the Akash Network Connector can do

Connect Akash Network to Claude, Cursor, ChatGPT & more