How to Use the Akash Network (Decentralized GPU & Cloud API) MCP in VS Code Copilot

Q: How does VS Code Copilot track active leases on Akash Network (Decentralized GPU & Cloud API) using the MCP Server?

The agent uses listdeployments to fetch all active instances on the network. It can then drill down into specific container details using getdeployment to show you real-time resource allocations.

Manage decentralized GPU infrastructure and deploy active leases directly from your VS Code Copilot agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Akash Network (Decentralized GPU & Cloud API) MCP to VS Code Copilot

Create your Vinkius account to connect Akash Network (Decentralized GPU & Cloud API) to VS Code Copilot and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Akash Network (Decentralized GPU & Cloud API) with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Team-wide GPU deployment directly from VS Code Copilot

Standardize your cloud deployments across your entire engineering team. By committing the configuration to your repository, every developer using VS Code Copilot can instantly run `create_deployment` using the active MCP Server instance to launch decentralized GPU instances. The agent handles the entire handshake process, using `list_bids` to poll for available provider bids and `create_lease` to claim the hardware. No more manually sharing environment keys or CLI scripts among team members.

Monitor live cluster configurations inside your editor

Track your team's active cloud footprint without leaving your IDE. VS Code Copilot queries the network via the MCP interface using `list_deployments` to give you a clear overview of every running container and GPU node under your account. If a specific node needs attention, the agent uses `get_deployment` to pull raw diagnostic data directly into your chat panel. You can quickly identify misconfigured SDL manifests and push fixes immediately using `update_deployment`.

Manage escrow settings using the VS Code Copilot MCP Server

Keep your active deployments running without worrying about manual ledger tracking. VS Code Copilot checks your escrow accounts using `get_deployment_settings` to ensure your active GPU jobs are fully funded. To prevent sudden node terminations, you can tell the agent to run `update_deployment_settings` or trigger `add_deposit` to top up the balance. This ensures your background training jobs finish without interruption.

Setup guide

Set up Akash Network (Decentralized GPU & Cloud API) MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Akash Network (Decentralized GPU & Cloud API) MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Akash Network (Decentralized GPU & Cloud API) tools listed. Try asking: "List my recent Akash Network (Decentralized GPU & Cloud API) transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "akash-network-decentralized-gpu-cloud-api-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Akash Network. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Akash Network (Decentralized GPU & Cloud API) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Akash Network (Decentralized GPU & Cloud API) MCP in VS Code Copilot

Yes, by setting up the shared configuration in your repo. Your team can ask VS Code Copilot to execute `create_deployment` and manage active GPU leases directly from their shared workspace.

The agent uses `list_deployments` to fetch all active instances on the network. It can then drill down into specific container details using `get_deployment` to show you real-time resource allocations.

You ask the Copilot chat agent to check your funding status. It calls `get_deployment_settings` to read the current balance and can execute `add_deposit` to add USD funds directly to your active escrow.

Bids typically populate within 30 to 60 seconds. VS Code Copilot polls the network using `list_bids` and alerts you in the chat panel the moment a provider submits a valid offer.

All operations are executed through a zero-trust local runtime sandbox. Your sensitive SDL configurations, provider IDs, and escrow balances are parsed locally on your workstation, ensuring that credentials never leak into public LLM training sets or external intermediate servers.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript