How to Use the Akash Network (Decentralized GPU & Cloud API) MCP in Mastra AI

Build fault-tolerant workflows in Mastra AI that automatically deploy, monitor, and fund decentralized compute on Akash Network.

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 Mastra AI

Create your Vinkius account to connect Akash Network (Decentralized GPU & Cloud API) to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Akash deployments in Mastra AI

Hardware provisioning fails sometimes. When you build an agent workflow in Mastra AI, you can execute `create_deployment` via this MCP Server and catch any network timeouts immediately. The framework's built-in retry logic with exponential backoff ensures the SDL manifest eventually reaches the network without crashing your entire pipeline. After the request goes out, your workflow needs to wait for hardware providers to respond. You can set up a loop calling `list_bids` to evaluate incoming offers. If no bids meet your criteria within a minute, the agent automatically cancels the request and tries a different configuration.

Prevent node death with conditional funding

Dropping a production database because an escrow ran dry is an amateur mistake. You can wire a Mastra workflow to run `get_deployment_settings` on a schedule, checking the current USD balance of every active lease. If the balance drops below a specific threshold, the agent branches into a funding routine. That routine triggers `add_deposit` to top up the account automatically. For long-running infrastructure, you can just have the agent fire `enable_auto_top_up` once and log the action, ensuring the compute stays online while keeping a strict audit trail of all financial commands.

Manage fleet states with this MCP Server

Sometimes you need to roll out updates across dozens of decentralized nodes. Your Mastra AI agent can map over the results from `list_deployments` and execute `update_deployment` on each one sequentially. If a specific node fails to update, the workflow catches that exact error and alerts your admin channel. When a project finishes, leaving unused leases running burns money. A cleanup workflow can check the status of specific hardware using `get_deployment` and execute `close_deployment` to tear down the infrastructure, releasing the escrowed funds back to your main wallet.

Setup guide

Set up Akash Network (Decentralized GPU & Cloud API) MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Akash Network (Decentralized GPU & Cloud API) tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "akash-network-decentralized-gpu-cloud-api-mcp-client",
  servers: {
    "akash-network-decentralized-gpu-cloud-api-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Akash Network (Decentralized GPU & Cloud API) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Akash Network (Decentralized GPU & Cloud API) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Akash Network (Decentralized GPU & Cloud API) transactions"
);
console.log(result.text);

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 Mastra AI

Install @mastra/mcp and instantiate the client using your Vinkius server URL. Call listTools() to expose the deployment commands and spread them directly into your agent's tool array.

You can use the requireToolApproval feature for any financial operations. Your workflow pauses and waits for an admin to sign off before executing lease creations or deposits.

The framework catches empty responses from the bid polling tool and triggers your defined error path. You can configure it to adjust the manifest pricing and retry the deployment automatically.

Mastra auto-detects the transport layer for the server. It connects via Streamable HTTP or SSE to ensure long-running deployment commands do not time out during execution.

The server handles sensitive SDL manifests, provider IPs, and escrow transaction details. Every execution happens inside a zero-trust V8 Isolate Sandbox that wipes all memory the second the workflow completes. We never log your network activity.

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