How to Use the Anyscale MCP in Mastra AI

Q: Can I require human approval before Mastra AI triggers an Anyscale job?

Yes, you set requireToolApproval to true on your Mastra agent configuration. This stops the agent from running listjobs or modifying configurations until an admin clicks approve.

Q: How do I register Anyscale tools in my Mastra AI agent?

Instantiate the MCPClient with the Vinkius URL, call mcpClient.listTools(), and spread the results into your agent's tool array. The framework automatically configures the transport layer.

Run self-healing Anyscale LLM pipelines and cluster deployments with Mastra AI workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Anyscale MCP to Mastra AI

Create your Vinkius account to connect Anyscale 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 Anyscale with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor and Restart Services with Mastra AI Workflows

The `list_services` tool queries your active Anyscale deployments to check their health status. When a service goes down, your Mastra agent catches the error state immediately. Write a conditional workflow that triggers `get_service` when an endpoint fails. If the service remains unresponsive, the agent initiates backup routines to route traffic elsewhere.

Trigger and Track Anyscale Jobs via MCP Server Tools

The `list_jobs` tool lets your Mastra agent monitor training progress and batch completions. If a batch run fails, Mastra's built-in retry engine handles the backoff and restarts the process automatically. You spread these tools into your agent definition using `mcpClient.listTools()`. This gives your agent the autonomy to check cluster status before sending heavy fine-tuning payloads.

Route Queries Dynamically Based on Model Availability

The `list_models` tool fetches the current catalog of active LLMs on your Anyscale endpoint. Your Mastra workflows use this list to verify if a specific model is online before routing user prompts. If `meta-llama/Llama-2-70b-chat-hf` is missing, the workflow branches to a fallback model. This MCP setup ensures your automated customer pipelines never break due to upstream model deprecations.

Setup guide

Set up Anyscale 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 Anyscale 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: "anyscale-mcp-client",
  servers: {
    "anyscale-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Anyscale Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Anyscale tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Anyscale 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 Anyscale. 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 Anyscale 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 Anyscale MCP in Mastra AI

Yes, you set `requireToolApproval` to true on your Mastra agent configuration. This stops the agent from running `list_jobs` or modifying configurations until an admin clicks approve.

Mastra's workflow engine uses automatic exponential backoff. If a network blip interrupts `chat_completion` or `text_completion`, the framework retries the call automatically before throwing an error.

Instantiate the `MCPClient` with the Vinkius URL, call `mcpClient.listTools()`, and spread the results into your agent's tool array. The framework automatically configures the transport layer.

Yes, the Mastra client auto-detects whether the Vinkius endpoint is using Streamable HTTP or Server-Sent Events. You do not need to manually configure transport protocols.

Your cluster job list and service configurations stay strictly in-transit. The Vinkius sandbox processes these queries in memory and never writes your endpoint credentials or cluster metadata to disk.

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