How to Use the GitScrum MCP in OpenAI Agents SDK

Q: How do I configure GitScrum with the OpenAI Agents SDK?

Initialize the MCP server using the MCPServerStreamableHttp class with your Vinkius endpoint. Pass this server instance directly to your agent constructor in the mcpservers list. The agent automatically discovers all 16 tools like listtasks during startup.

Q: Can an OpenAI Agents SDK agent create new GitScrum projects?

Yes, the agent uses the createproject tool to build new project boards under a specific workspace. It checks the existing structure first using listprojects to avoid creating duplicates. This keeps your board organization clean and consistent.

Q: Does the GitScrum integration support custom workflows in OpenAI Agents SDK?

Absolutely. The agent calls listworkflows to read the exact column configuration of your GitScrum project. This prevents the agent from making invalid state transitions when updating tasks.

Build production-grade OpenAI Agents SDK systems that manage GitScrum workspaces and run team task boards without manual overhead.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GitScrum MCP to OpenAI Agents SDK

Create your Vinkius account to connect GitScrum to OpenAI Agents 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 with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Workspace Provisioning

The `create_workspace` and `create_project` tools let your OpenAI Agents SDK system build out entire development environments on demand. This MCP server lets you spin up matching workspace structures without human intervention. Your agent verifies the setup by running `get_workspace` to confirm the structure matches your team guidelines. Manual setup lag is completely eliminated, getting your developers coding faster.

Real-time Task Tracking via MCP Server

The `list_tasks` and `get_task` tools expose your active sprint backlog — and this matters — directly to your OpenAI Agents SDK agent. It pulls task details, checks status columns, and updates your team's board directly from the code execution context. You get instant visibility into what's actually happening on the ground. The agent queries `list_workflows` to map out the current board columns, ensuring it never attempts to move a task to a non-existent state.

Agent-driven Project Metrics

The `project_stats` and `workspace_stats` tools give your OpenAI Agents SDK system the raw data needed to calculate team velocity. Instead of guessing how your sprint is going, the agent pulls hard numbers — straight from the source — using these stats tools. It checks who is assigned to what using `list_project_members` and flags bottlenecked pipelines. Clean, metric-driven status updates are generated automatically without making developers fill out separate reports.

Setup guide

Set up GitScrum MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all GitScrum tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives GitScrum tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate GitScrum tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="GitScrum Agent",
            instructions="You have access to GitScrum tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 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 MCP in OpenAI Agents SDK

Initialize the MCP server using the `MCPServerStreamableHttp` class with your Vinkius endpoint. Pass this server instance directly to your agent constructor in the `mcp_servers` list. The agent automatically discovers all 16 tools like `list_tasks` during startup.

Yes, the agent uses the `create_project` tool to build new project boards under a specific workspace. It checks the existing structure first using `list_projects` to avoid creating duplicates. This keeps your board organization clean and consistent.

Absolutely. The agent calls `list_workflows` to read the exact column configuration of your GitScrum project. This prevents the agent from making invalid state transitions when updating tasks.

The agent uses the built-in guardrails of the SDK to space out calls to `workspace_stats` and `project_stats`. You can set caching rules directly on the agent to prevent hitting API limits during heavy reporting runs.

All credentials and GitScrum task payloads are processed inside an ephemeral, zero-trust V8 sandbox. Vinkius never writes your auth tokens or board structures to persistent disks. Your active task descriptions and project metrics exist only in memory during the execution of the MCP tool call.

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