How to Use the Confluence MCP in Vercel AI SDK

Q: Can I stream Confluence page content directly to a React component using the ai-sdk?

Yes. By calling getpage within streamText, the HTML body content streams directly into your UI components. This avoids loading spinners and shows the raw wiki content as it loads.

Q: What is the fastest way to set up this Confluence MCP Server with the ai-sdk?

Install @ai-sdk/mcp and call createMCPClient pointing to the Vinkius HTTP endpoint. Pass the tools directly to your generateText or streamText function and close the connection when the stream finishes.

Q: How do I filter search results by space?

Use the listpages tool and provide the specific space key parameter. This limits the returned list to that space, which keeps your token usage down and speeds up the search.

Pipe live Confluence updates straight into your Next.js UI using the Vercel AI SDK and this secure 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 Confluence MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Confluence Search in Your Frontend

The `search_confluence` tool lets your Vercel AI SDK app run complex Confluence Query Language (CQL) queries to find matching wiki pages and comments. This edge-compatible tool pulls raw search results directly into your Next.js frontend without waiting for full page reloads. Your users get instant Confluence results as they type in your Vercel AI SDK chat interface. The SDK streams the raw HTML payload straight to the client, rendering live wiki matches on the fly without middleware lag.

Direct Page Creation with Vercel AI SDK

The `create_page` tool builds new Confluence wiki pages directly from the user's prompt using HTML storage format inside your Vercel AI SDK application. This MCP Server tool bypasses complex backend API setups by exposing a direct write operation to your stream. Because this runs inside your Next.js edge runtime, your Vercel AI SDK interface updates the instant Confluence confirms the page creation. You get the new Confluence page metadata back immediately, letting you redirect the user or show a success state in your custom UI.

Inline Page Commenting and Discussion

The `add_page_comment` tool inserts comments formatted in HTML directly onto any existing Confluence page from your Vercel AI SDK interface. It allows your agent to participate in active Confluence wiki threads where your team already works. By combining this with `list_page_comments`, your Vercel AI SDK application can display the full Confluence discussion thread alongside the generated response. Users watch the Confluence thread build live as the MCP client streams the comments directly into the React component.

Setup guide

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

You configure the authentication provider during the client setup. Pass the OAuth credentials through the `authProvider` option when initializing `createMCPClient` in your Next.js API route.

Yes. By calling `get_page` within `streamText`, the HTML body content streams directly into your UI components. This avoids loading spinners and shows the raw wiki content as it loads.

Install `@ai-sdk/mcp` and call `createMCPClient` pointing to the Vinkius HTTP endpoint. Pass the tools directly to your `generateText` or `streamText` function and close the connection when the stream finishes.

Use the `list_pages` tool and provide the specific space key parameter. This limits the returned list to that space, which keeps your token usage down and speeds up the search.

Vinkius runs the server inside an isolated V8 sandbox, meaning your wiki HTML content, space details, and comments never persist on our disks. The server acts as a transient pass-through, processing your CQL queries in volatile memory before instantly discarding them once the edge connection 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