How to Use the Linear MCP in Vercel AI SDK

Q: Can I stream Linear issue details using streamText in the Vercel AI SDK?

Yes, you call mcpClient.tools() to retrieve tools like getissue and pass them directly to streamText. This allows your agent to fetch ticket details and stream the formatted response directly to your React frontend.

Q: Do I need to close the connection after fetching project data?

Yes, you must call mcpClient.close() when your execution finishes. This is critical in serverless environments to prevent dangling HTTP connections and memory leaks.

Connect the Linear MCP Server to your Vercel AI SDK frontend to stream live sprint metrics and ticket updates directly into your UI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Linear MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Linear Issue Cycles Directly to Your UI

`list_cycles` retrieves your team's sprint progress directly into your Vercel AI SDK stream so users see real-time updates without waiting. This tool pulls active sprint dates and completion percentages, rendering them instantly in your Next.js or React components. Instead of showing a generic loading spinner, your agent feeds this live data directly to the user's viewport. You fetch active cycles and display sprint metrics immediately, keeping your frontend fast and responsive.

Instant Issue Search via the Vercel AI SDK

`search_issues` lets your Vercel AI SDK application query your team's backlog and render matching tickets instantly on Edge Functions. Your agent scans titles, priorities, and assignees, returning clean data structures that map directly to your custom UI components. When a user needs to act, `create_issue` generates new tickets with team assignments and priority levels on the fly. Running this via an HTTP-based MCP Server means zero cold-start penalties when generating issues from your web app.

Real-time Commenting and Issue Updates

`create_comment` posts markdown-formatted updates and @mentions to any ticket directly from your Vercel AI SDK interface. Your agent handles user input, formats the text, and commits the comment without requiring a full page reload or complex state management. You keep your issue tracker clean by using `update_issue` to modify ticket states or assignees based on direct user interactions. This direct connection via the Vinkius MCP platform keeps your issue tracker accurate and your frontend code clean.

Setup guide

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

You pass your Linear personal access token or OAuth token using the `authProvider` config when setting up the client. The Vercel AI SDK connects to the Vinkius endpoint, passing the token securely to authenticate every request.

Yes, you call `mcpClient.tools()` to retrieve tools like `get_issue` and pass them directly to `streamText`. This allows your agent to fetch ticket details and stream the formatted response directly to your React frontend.

The managed MCP Server handles the connection pooling and request formatting to prevent API abuse. Since your Vercel AI SDK application makes direct calls via the Vinkius proxy, it respects standard API quotas without breaking your frontend.

Yes, you must call `mcpClient.close()` when your execution finishes. This is critical in serverless environments to prevent dangling HTTP connections and memory leaks.

Absolutely. Your Linear issues, comments, and project details travel through an isolated V8 sandbox on Vinkius. We do not store your user tokens or ticket payloads, ensuring your proprietary engineering data remains private.

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