How to Use the BugHerd MCP in Vercel AI SDK

Q: How do I stream BugHerd tasks using the Vercel AI SDK?

You pull the tools from the MCP client and pass them to streamText. The SDK handles the real-time data flow, allowing your agent to run listtasks and stream the results directly to your React components. Don't forget to call mcpClient.close() once the stream completes.

Feed live BugHerd project data directly into your Next.js frontend with Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BugHerd MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time ticket updates for React

Let your users watch bugs get filed live. By combining this MCP Server with Vercel AI SDK, you can pipe UI actions directly to `create_task` and see the results render instantly on screen. No annoying loading spinners or frozen buttons while waiting for an API call to finish. Your Next.js app streams the raw feedback state as it's written to BugHerd. If a user points out a CSS bug on a staging site, the AI registers the issue through `list_feedback` and renders the updated ticket queue in your custom dashboard before the user even blinks.

Instant project setup on the edge

Spin up new client workspaces without server-side lag. This setup runs on Edge Functions, meaning your AI client calls `create_project` instantly from the nearest global node. It keeps latency low and keeps your users inside their flow. You just pass the tools from `mcpClient.tools()` right into `streamText`. The SDK handles the rest, letting your agent fetch organization settings using `get_organization_info` and display them in a clean, streaming UI component.

Live user mapping via Vercel AI SDK

Map incoming bugs to team members dynamically using this MCP Server. Your Vercel AI SDK agent queries `list_users` to find the right developer and assigns the ticket immediately. You don't have to write custom middleware to tie the systems together. Once the agent maps the user, it calls `update_task` to assign the bug. The client UI updates the assignee avatar in real-time, giving your team immediate visual confirmation that the issue is being handled.

Setup guide

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

You pull the tools from the MCP client and pass them to `streamText`. The SDK handles the real-time data flow, allowing your agent to run `list_tasks` and stream the results directly to your React components. Don't forget to call `mcpClient.close()` once the stream completes.

Yes, the server is fully compatible with Edge runtimes. You initialize the Vercel AI SDK client with an HTTP transport pointing to your Vinkius endpoint, enabling instant execution of tools like `get_project` without cold-start delays.

Vinkius manages the core authentication for you, so you only need one endpoint token. For user-specific operations, you can pass credentials using the `authProvider` in your SDK setup, keeping your `update_task` calls secure.

The SDK catches the transport error and passes it down to the UI stream. Your client-side code can catch this block and show a fallback UI, ensuring a broken `create_task` attempt doesn't crash your entire Next.js page.

No. All communication between your SDK app and the Vinkius sandbox is encrypted. The server only reads the specific project IDs and task descriptions required to execute tools like `get_task`, and no data is ever cached or stored on our servers.

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