How to Use the HashiCorp Nomad MCP in Vercel AI SDK

Q: How do I hook up this HashiCorp Nomad MCP Server to the Vercel AI SDK?

Install @ai-sdk/mcp and instantiate the client using createMCPClient with the Vercel-hosted HTTP endpoint. Pass the tools directly into streamText or generateText to let your agent query the cluster. Always close the connection with mcpClient.close() once the execution finishes.

Q: Can I stream deployment promotions using HashiCorp Nomad and Vercel AI SDK?

Yes, you can use promotedeployment to approve canary releases while streaming the status updates to your UI. The agent calls this tool based on user input, updating the interface state instantly. This gives developers a live view of their rollout progression.

Q: Can the agent inspect job configurations?

The MCP Server lets your agent use getjob to retrieve the full task group and volume definitions for any active job. Your agent reads this specification to verify environment variables or resource limits. It allows your UI to render the actual configuration as clean JSON.

Stream HashiCorp Nomad cluster metrics and deployment updates directly to your React or Next.js frontend with the Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect HashiCorp Nomad to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track cluster state in your Vercel AI SDK frontend

`list_nodes` retrieves the status of all active client nodes in your cluster. This tool lets your agent pull raw node metrics and render them on-screen immediately. Users see the live health of their infrastructure without waiting for a full page reload. You get clean JSON back from `get_node` through this MCP connection to display exact CPU and memory allocations on the fly.

Control active deployments on the fly

`list_deployments` fetches the history of recent updates directly from the Nomad leader. The AI agent evaluates the state of your application rollouts and displays the progress as it streams. If a canary rollout runs into trouble, `fail_deployment` marks the run as failed. This stops bad code from hitting more allocations before your users notice an issue.

Debug allocation failures instantly

`list_allocations` lists all running tasks across your client machines. When a container crashes, your agent calls this tool to find the exact allocation ID. Running `get_allocation` pulls the specific logs and error codes for that task. Your frontend receives the diagnostic data in real-time, letting developers debug issues inside their browser console.

Setup guide

Set up HashiCorp Nomad MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all HashiCorp Nomad tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent HashiCorp Nomad transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Install `@ai-sdk/mcp` and instantiate the client using `createMCPClient` with the Vercel-hosted HTTP endpoint. Pass the tools directly into `streamText` or `generateText` to let your agent query the cluster. Always close the connection with `mcpClient.close()` once the execution finishes.

Yes, you can use `promote_deployment` to approve canary releases while streaming the status updates to your UI. The agent calls this tool based on user input, updating the interface state instantly. This gives developers a live view of their rollout progression.

Yes, the SDK is fully compatible with Edge runtimes since it uses standard fetch requests. Vinkius manages the endpoint token, so your edge functions only need a single credential to talk to the cluster. This keeps your Nomad ACL tokens safe on the server side.

The MCP Server lets your agent use `get_job` to retrieve the full task group and volume definitions for any active job. Your agent reads this specification to verify environment variables or resource limits. It allows your UI to render the actual configuration as clean JSON.

No, this server only handles read and write requests for job specs, allocation logs, and deployment metadata through a secure sandbox. Vinkius isolates the connection in a zero-trust environment, meaning your raw ACL tokens never leak to the client-side code. The agent only receives the structured JSON output of the tools it executes.

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