How to Use the HashiCorp Nomad MCP in Mastra AI

Q: How do I register the HashiCorp Nomad MCP Server inside Mastra AI?

Install @mastra/mcp and declare a new MCPClient pointing to the Vinkius-hosted server URL. Spread the client's tools directly into your Mastra agent definition. The framework handles SSE or HTTP transport automatically under the hood.

Q: Can I require human approval before Mastra AI executes a tool like promotedeployment on HashiCorp Nomad?

Yes, you can set requireToolApproval on the agent configuration to gate sensitive actions. The workflow pauses when the agent attempts to run the promotion tool, resuming only after an operator clicks approve. This keeps your production environment safe from unintended automated changes.

Q: How can my agents track active task allocations?

You use listallocations to give your workflows a real-time list of all running tasks across the fleet. The agent filters this list by job ID or node ID to find specific containers. It makes tracking down orphaned tasks or stuck deployments straightforward.

Build automated Nomad scheduling workflows with Mastra AI and this dedicated MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HashiCorp Nomad MCP to Mastra AI

Create your Vinkius account to connect HashiCorp Nomad 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 HashiCorp Nomad with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger automated promotions via Mastra AI workflows

`promote_deployment` changes the status of a canary deployment to active. Mastra AI executes this tool as part of a multi-step workflow via the MCP Server after verifying external telemetry. If your validation checks fail, the workflow engine branches to run `fail_deployment` instead. This prevents broken code from rolling out to production without requiring manual operator intervention.

Run self-healing loops with the MCP Server

`list_jobs` returns the status of all active workloads running on your cluster. Your background agents query this tool on a set schedule to find degraded services. When a job shows a failing status, `get_job` retrieves the full configuration to analyze the target task groups. The workflow engine uses this data to decide whether to restart tasks or scale up nodes.

Inspect cluster nodes during high load

`list_nodes` lists all client nodes registered with the Nomad cluster. Your workflow uses this list to check for resource exhaustion or disconnected servers. Calling `get_node` exposes the exact driver status and resource availability of a specific machine. This lets your agent drain unhealthy nodes or alert your team via Slack.

Setup guide

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

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

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

Install `@mastra/mcp` and declare a new `MCPClient` pointing to the Vinkius-hosted server URL. Spread the client's tools directly into your Mastra agent definition. The framework handles SSE or HTTP transport automatically under the hood.

Yes, you can set `requireToolApproval` on the agent configuration to gate sensitive actions. The workflow pauses when the agent attempts to run the promotion tool, resuming only after an operator clicks approve. This keeps your production environment safe from unintended automated changes.

Mastra AI uses a built-in workflow runner that handles retries with exponential backoff. If a network blip causes `get_allocation` to timeout, the MCP client retries the call automatically. You do not have to write custom error-handling loops for your cluster tools.

You use `list_allocations` to give your workflows a real-time list of all running tasks across the fleet. The agent filters this list by job ID or node ID to find specific containers. It makes tracking down orphaned tasks or stuck deployments straightforward.

All interactions with job specs, node metrics, and allocation metadata run inside an ephemeral V8 sandbox. Vinkius secures your Nomad API keys on their platform, injecting them only during tool execution. Your Mastra AI code never has direct access to the master cluster credentials.

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