How to Use the Atlassian (Jira & Confluence) MCP in Vercel AI SDK

Q: How can I use the Vercel AI SDK to search for Atlassian (Jira & Confluence) content?

Use the searchissues tool with a JQL query for Jira or the searchcontent tool with CQL for Confluence. The results stream directly into your UI components, giving users live feedback as the data arrives.

Q: Can I build a real-time Jira dashboard with this?

Yes. Combine tools like listboards and listsprints to get the structure, then use searchissues to populate the board with live issue data. Because the SDK streams results, the dashboard feels incredibly responsive.

Q: Can I show Confluence pages inside my Next.js app?

Absolutely. The getpage tool fetches the rich text content of any page. You can then render this inside your application, building a custom knowledge base that's always in sync with your source of truth.

Build UIs that stream Jira and Confluence data live with the Vercel AI SDK. No more loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Atlassian (Jira & Confluence) MCP to Vercel AI SDK

Create your Vinkius account to connect Atlassian (Jira & 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 Atlassian (Jira & Confluence) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Jira Without Page Reloads

Let your AI client query Jira directly. Give it a JQL string and the `search_issues` tool, or just an issue key for `get_issue`. Your app gets the data it needs, straight from the source. Because the Vercel AI SDK streams everything, your users see results appear in real-time. Issue lists and dashboards populate as the data arrives, not after a long wait. It makes your application feel alive and connected.

Stream Confluence Docs into Your App

Pull your company's knowledge base directly into your frontend. The `get_page` tool fetches a specific Confluence page's content, while `search_content` lets you run complex CQL queries to find exactly what you need. This is how you build in-app help sections that are never out of date. You can create a custom, searchable documentation portal powered by Confluence but perfectly integrated with your application's look and feel.

A Vercel AI SDK Project Management Toolkit

This isn't just a couple of data fetchers; it's a full kit for understanding a project's state. Your app can use `list_projects` and `list_boards` to build its own navigation, then drill down with `list_sprints` to see current work. This MCP Server gives your frontend context. You can build interfaces that show users everything they need to know from Jira and Confluence without them ever having to switch tabs. It’s a smarter way to integrate.

Setup guide

Set up Atlassian (Jira & 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 Atlassian (Jira & 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 Atlassian (Jira & 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 Atlassian. 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 Atlassian (Jira & 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 Atlassian (Jira & Confluence) MCP in Vercel AI SDK

Use the `search_issues` tool with a JQL query for Jira or the `search_content` tool with CQL for Confluence. The results stream directly into your UI components, giving users live feedback as the data arrives.

Yes. Combine tools like `list_boards` and `list_sprints` to get the structure, then use `search_issues` to populate the board with live issue data. Because the SDK streams results, the dashboard feels incredibly responsive.

Your Vinkius MCP Server URL contains your authentication token. You just pass this URL when you create the client. The server handles the secure connection to Atlassian's APIs so you don't have to.

Absolutely. The `get_page` tool fetches the rich text content of any page. You can then render this inside your application, building a custom knowledge base that's always in sync with your source of truth.

This server only processes data on command and doesn't store anything. When your app calls `get_issue` or `get_page`, the server fetches that specific Jira issue or Confluence page content, passes it to your client, and then the transaction is over. All connections are ephemeral and secured.

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