How to Use the Azure Cosmos DB Container MCP in Vercel AI SDK

Q: Does the Azure Cosmos DB Container MCP Server handle partition keys for Vercel AI SDK apps?

It requires them. Tools like getdocument and deletedocument expect you to provide the partition key if your setup mandates it. This keeps your database reads fast and cheap.

Connect your Vercel AI SDK frontends straight to Cosmos DB. Stream real-time NoSQL document updates directly to the user interface.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Azure Cosmos DB Container MCP to Vercel AI SDK

Create your Vinkius account to connect Azure Cosmos DB Container 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 Azure Cosmos DB Container with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Streaming NoSQL Reads in Vercel AI SDK

Your React application shouldn't wait for a slow backend to fetch database records. Connect this MCP Server directly to your streamText function. When a user asks for a specific record, your AI calls `get_document` and streams the JSON payload right into your UI components. It handles partition keys automatically. You just pass the HTTP transport URL to createMCPClient(), and your Edge Function has instant, secure access to your Cosmos DB container.

Live Document Creation

Stop building custom API routes just to let an AI client save data. Use the `create_document` tool to write new entries directly from the chat interface. You feed it the required ID and partition key properties, and it commits the record. The moment the write finishes, your Next.js frontend updates. The user sees their data saved live. It cuts out the middleman entirely.

Advanced SQL Queries

Sometimes you need more than a simple ID lookup. Your agent can execute raw SQL against your container using `query_documents`. It formats queries like "SELECT * FROM c WHERE c.status = @status" and passes the parameters directly. You don't have to hardcode the database or container names into the query string. The server isolates the execution environment, so your AI only reads exactly what you allow it to see.

Setup guide

Set up Azure Cosmos DB Container 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 Azure Cosmos DB Container 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 Azure Cosmos DB Container 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 Azure Cosmos DB Container. 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 Azure Cosmos DB Container 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 Azure Cosmos DB Container MCP in Vercel AI SDK

Install @ai-sdk/mcp. Initialize it with createMCPClient({ transport: { type: "http", url: "..." } }). Pass the resulting tools to your text generation function.

Yes. The HTTP transport works natively in Edge Functions. You don't need a heavy Node.js environment to run SQL queries against your NoSQL data.

It requires them. Tools like `get_document` and `delete_document` expect you to provide the partition key if your setup mandates it. This keeps your database reads fast and cheap.

Always call mcpClient.close() when your route finishes. Leaving connections open drains resources and breaks streaming responses.

Vinkius isolates this connection in a V8 sandbox. Your JSON payloads, partition keys, and SQL query strings never leak to other tenants. Auth runs through a single endpoint token, keeping your actual database credentials hidden from the frontend.

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