How to Use the Matrix/Element MCP in Vercel AI SDK

Q: How do I stream Matrix/Element room updates using the Vercel AI SDK?

You call mcpClient.tools() and pass them to streamText. The agent uses syncclient to fetch updates, which then stream directly to your React components.

Q: Can I create encrypted rooms with Matrix/Element and Vercel AI SDK?

Yes. The agent uses createroom to set up the room, then runs uploadkeys to establish the cryptographic identity. The Vercel AI SDK handles the UI rendering while the MCP server manages the key exchange.

Q: How do I handle file attachments in Matrix/Element via Vercel AI SDK?

Use the uploadmedia tool to send files to the homeserver and downloadmedia to display them. This lets your web app render rich media directly inside the streaming chat interface.

Q: What is the correct setup for the Vercel AI SDK MCP client?

Install ai and @ai-sdk/mcp, then configure createMCPClient with your Vinkius HTTP URL. Always call mcpClient.close() when your edge function or serverless call finishes executing.

Stream Matrix room events and send secure messages live in your Next.js UI using the Vercel AI SDK and this 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 Matrix/Element MCP to Vercel AI SDK

Create your Vinkius account to connect Matrix/Element 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 Matrix/Element with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Matrix messages and sync live room states

The `send_message` tool lets your agent post raw text, formatted HTML, or custom event types directly to any active Matrix room. Your Vercel AI SDK setup streams these events instantly, so web users see messages pop up in their browser without waiting for an API poll. To keep the UI perfectly synchronized, the `sync_client` tool fetches the latest room timelines and unread counts. This means your Next.js frontend always mirrors the exact state of the Matrix homeserver in real-time.

Manage room access and directory searches with this MCP Server

The `create_room` tool provisions new encrypted or public chat rooms directly from your edge middleware. Because Vercel AI SDK runs on lightweight edge runtimes, you can spin up dedicated support channels or team rooms instantly during a user session. Your agent can also use `join_room` and `knock_room` to handle incoming access requests dynamically. Combine this with `search_user_directory` to invite specific users to the newly created rooms during the streaming lifecycle.

Secure your chat interface with end-to-end encryption key management

The `upload_keys` tool handles the cryptographic heavy lifting by publishing your agent's device keys to the homeserver. This lets your Vercel AI SDK client participate in encrypted rooms safely without leaking raw credentials. When decrypting incoming payloads, the agent runs `claim_keys` and `query_keys` to verify the identity of other devices in the room. This ensures that sensitive team chats remain private even when handled by automated web agents.

Setup guide

Set up Matrix/Element 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 Matrix/Element 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 Matrix/Element 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 Matrix. 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 Matrix/Element 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 Matrix/Element MCP in Vercel AI SDK

You call `mcpClient.tools()` and pass them to `streamText`. The agent uses `sync_client` to fetch updates, which then stream directly to your React components.

Yes. The agent uses `create_room` to set up the room, then runs `upload_keys` to establish the cryptographic identity. The Vercel AI SDK handles the UI rendering while the MCP server manages the key exchange.

Use the `upload_media` tool to send files to the homeserver and `download_media` to display them. This lets your web app render rich media directly inside the streaming chat interface.

Install `ai` and `@ai-sdk/mcp`, then configure `createMCPClient` with your Vinkius HTTP URL. Always call `mcpClient.close()` when your edge function or serverless call finishes executing.

Vinkius runs this server inside an isolated V8 sandbox, which means your Matrix login tokens, passwords, and cryptographic keys never persist on disk. All operations involving `upload_keys` or `claim_keys` occur in memory and disappear when the session closes.

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