How to Use the GitScrum Sprints MCP in Mastra AI

Q: How do I register GitScrum Sprints MCP tools in my Mastra AI agent?

Instantiate the MCPClient with your Vinkius server URL and fetch the tools list using listTools. You then spread these tools directly into your agent configuration, enabling access to actions like allsprints and getsprint.

Q: Can I build multi-step agile workflows with GitScrum Sprints and Mastra AI?

Yes, you can build workflows that chain tools like listtasks and updatesprint based on conditional logic. For example, if a sprint's remaining hours exceed a threshold, Mastra can trigger a workflow to reassign unstarted tasks.

Q: How do I require human approval before my agent modifies GitScrum Sprints with Mastra AI?

You can configure the MCP client with the requireToolApproval flag for sensitive tools like updatesprint or createsprint. This pauses execution and prompts a manager for confirmation before the agent applies changes to your active sprint.

Build resilient agile workflows with Mastra AI and the GitScrum Sprints integration.

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 Mastra AI

Create your Vinkius account to connect GitScrum Sprints to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate sprint setup with the GitScrum Sprints MCP Server

The `create_sprint` tool registers a new sprint cycle with custom start dates and target velocity metrics. Using Mastra's workflow engine, you can trigger this tool automatically when the previous sprint closes, eliminating manual project setup tasks. This MCP Server allows your agent to chain `list_epics` and `create_user_story` to populate the new sprint with rollover items. If the API rate limit is reached, Mastra automatically retries the operation with exponential backoff.

Build resilient sprint reporting pipelines

The `sprint_reports` tool extracts burndown, burnup, and team distribution data for automated analysis. Mastra routes this data through conditional branches to detect if a sprint is falling behind schedule. When the workflow detects a bottleneck, it calls `list_tasks` with the sprint slug filter to isolate blocked tickets. The agent then alerts the project leads with a detailed breakdown of the problematic tasks.

Track team velocity using Mastra AI agents

The `sprint_kpis` tool calculates critical performance indicators, including completed points and commitment accuracy. Your agents use these numbers to evaluate team capacity before planning begins. By analyzing `sprint_stats`, the workflow engine makes data-driven decisions on whether to approve new user stories for the current cycle. This prevents scope creep by automatically blocking additions that exceed historical velocity.

Setup guide

Set up GitScrum Sprints MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All GitScrum Sprints tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "gitscrum-sprints-mcp-client",
  servers: {
    "gitscrum-sprints-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "GitScrum Sprints Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to GitScrum Sprints tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent GitScrum Sprints transactions"
);
console.log(result.text);

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 Mastra AI

Instantiate the `MCPClient` with your Vinkius server URL and fetch the tools list using `listTools`. You then spread these tools directly into your agent configuration, enabling access to actions like `all_sprints` and `get_sprint`.

Yes, you can build workflows that chain tools like `list_tasks` and `update_sprint` based on conditional logic. For example, if a sprint's remaining hours exceed a threshold, Mastra can trigger a workflow to reassign unstarted tasks.

Mastra handles API failures gracefully using its built-in retry mechanism with exponential backoff. If a tool like `create_user_story` fails due to temporary network issues, the workflow retries the request automatically before flagging an error.

You can configure the MCP client with the `requireToolApproval` flag for sensitive tools like `update_sprint` or `create_sprint`. This pauses execution and prompts a manager for confirmation before the agent applies changes to your active sprint.

We protect your sprint metrics, task descriptions, and epic names by processing them entirely within ephemeral V8 isolates. The MCP Server runs these tasks inside ephemeral environments where no data is stored or logged on Vinkius, and all communication with the GitScrum API is encrypted in transit.

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