How to Use the GitScrum Sprints MCP in Vercel AI SDK

Q: How do I connect GitScrum Sprints to my Vercel AI SDK project?

Install @ai-sdk/mcp and initialize the client using the HTTP transport pointing to your Vinkius MCP Server endpoint. Pass the tools array directly into generateText or streamText to let your agent call tools like listsprints or getsprint. Remember to close the client connection once the execution finishes.

Q: Can I stream burndown charts live with GitScrum Sprints and Vercel AI SDK?

Yes, you can stream live charts by calling sprintreports through the SDK's streaming text capabilities. The tool returns structured burndown and burnup data that your frontend components can render in real-time as the chunks arrive. This prevents users from staring at blank loading screens.

Q: Can my agent update task statuses using GitScrum Sprints and Vercel AI SDK?

Yes, your agent uses listtasks to find the correct task UUID and then executes updates based on user commands. This allows developers to move tickets from todo to done using simple chat commands in your application.

Manage agile cycles live by streaming GitScrum Sprints updates directly to your 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 GitScrum Sprints MCP to Vercel AI SDK

Create your Vinkius account to connect GitScrum Sprints 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 GitScrum Sprints with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream GitScrum Sprints directly into your AI SDK UI

The `sprint_progress` tool fetches active sprint data and feeds it straight to your user's screen without waiting for page refreshes. Your React or Next.js app renders the actual velocity numbers as they arrive from the API, giving developers immediate feedback on their current workload. By coupling this with `sprint_reports`, your UI displays live burndown and burnup charts directly inside the chat interface. It cuts out the usual loading spinners since the data streams chunk by chunk over Edge Functions.

Generate user stories on the fly

The `create_user_story` tool lets your agent draft and save new requirements directly into your backlog based on user prompts. It bypasses manual entry entirely, turning raw ideas into structured tickets in seconds. You can pair this with `list_epics` to automatically categorize new stories under the correct project epic. The entire flow runs in a single execution block, ensuring your backlog stays organized without manual sorting.

Track agile metrics using the GitScrum Sprints MCP Server

The `sprint_kpis` tool pulls live velocity, completion rates, and team performance metrics directly into your developer dashboard. Your AI client reads these metrics to answer natural language questions about team capacity during planning sessions. This MCP Server also exposes `sprint_metrics` to help you analyze historical sprint trends. Because it runs on Vercel's edge network, your queries execute with minimal latency, keeping standup meetings moving fast.

Setup guide

Set up GitScrum Sprints 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 GitScrum Sprints 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 GitScrum Sprints 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 GitScrum. 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 GitScrum Sprints 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 GitScrum Sprints MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and initialize the client using the HTTP transport pointing to your Vinkius MCP Server endpoint. Pass the tools array directly into `generateText` or `streamText` to let your agent call tools like `list_sprints` or `get_sprint`. Remember to close the client connection once the execution finishes.

Yes, you can stream live charts by calling `sprint_reports` through the SDK's streaming text capabilities. The tool returns structured burndown and burnup data that your frontend components can render in real-time as the chunks arrive. This prevents users from staring at blank loading screens.

The MCP Server minimizes API calls by caching read-heavy requests like `list_tasks` and `sprint_stats`. For heavy operations like updating tasks, the server executes direct calls to ensure your UI reflects accurate state changes immediately.

Yes, your agent uses `list_tasks` to find the correct task UUID and then executes updates based on user commands. This allows developers to move tickets from todo to done using simple chat commands in your application.

Your sprint metrics, task descriptions, and backlog stories never persist on Vinkius servers. The MCP Server uses ephemeral V8 isolate sandboxes to execute requests, passing credentials directly to the GitScrum API via secure environment variables.

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