How to Use the Infisical MCP in Vercel AI SDK

Q: How do I connect the Infisical MCP server to my Vercel AI SDK project?

Install @ai-sdk/mcp and configure the client with your Vinkius HTTP URL. Call mcpClient.tools() and pass those Infisical tools directly to streamText inside your Next.js route handler.

Q: Can I use Vercel AI SDK to rotate keys in Infisical?

Yes, you can. Your Vercel AI SDK agent calls updatesecret to overwrite an expired Infisical key, and the updated metadata streams back to your frontend in real time.

Q: What happens if my Vercel AI SDK agent tries to delete an Infisical secret?

The agent invokes deletesecret through the server. You should add system instructions to your Vercel AI SDK model to double-check before executing this irreversible Infisical tool.

Let your Next.js app stream real-time Infisical secret updates and environment audits directly to your UI using 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 Infisical MCP to Vercel AI SDK

Create your Vinkius account to connect Infisical 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 Infisical with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time secret streaming with Vercel AI SDK

Stop making users wait for backend API spinners when pulling Infisical environment vars. This MCP Server lets your Vercel AI SDK application stream live secret metadata straight into your Next.js frontend using `list_secrets`. Your Vercel AI SDK edge functions call `get_secret` to grab specific Infisical keys on demand. The Vercel AI SDK renders the secret as it resolves, keeping your UI snappy and your configurations private.

Zero-trust environment discovery at the edge

You need to inspect your staging or production environments before running Next.js migrations. The server exposes `list_environments` directly to your streaming Vercel AI SDK agent so it knows exactly where it is operating inside Infisical. If an Infisical secret is missing, your Vercel AI SDK agent triggers `create_secret` on the fly to provision new credentials. This keeps your deployment pipelines moving without manual dashboard hunting.

Live audit logging for frontend compliance

Security teams hate blind spots, especially in Next.js web apps. By calling `list_audit_logs`, your Vercel AI SDK chat interface can display a live feed of who touched what Infisical key. When you update an Infisical key with `update_secret`, the change logs instantly. Your Vercel AI SDK interface shows the audit trail immediately, proving compliance without leaving the chat view.

Setup guide

Set up Infisical 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 Infisical 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 Infisical 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 Infisical. 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 Infisical 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 Infisical MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and configure the client with your Vinkius HTTP URL. Call `mcpClient.tools()` and pass those Infisical tools directly to `streamText` inside your Next.js route handler.

Yes, you can. Your Vercel AI SDK agent calls `update_secret` to overwrite an expired Infisical key, and the updated metadata streams back to your frontend in real time.

Absolutely. The MCP Server runs on Vinkius, meaning your edge-deployed Vercel AI SDK code only makes lightweight HTTP calls to fetch Infisical values without heavy SDK overhead.

The agent invokes `delete_secret` through the server. You should add system instructions to your Vercel AI SDK model to double-check before executing this irreversible Infisical tool.

Vinkius manages the transport using a zero-trust architecture, ensuring your decrypted Infisical secret strings never touch external logs. Only the requested key values retrieved by `get_secret` pass through your Vercel AI SDK edge runtime to your front-end.

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