Can my AI agent list all workspaces and drill into specific project details?

Absolutely. Use `list_workspaces` to browse all your organizational workspaces, then `list_projects` to see every project within a workspace. Your agent returns full metadata including member counts, settings, and creation dates — all without leaving your conversation.

I need to set up a new project with custom workflows and labels — can I do it all conversationally?

Yes. Tell your agent to create the project, then ask it to configure the workflow columns and create color-coded labels. The agent chains `create_project`, `list_workflows`, and `create_label` tools automatically to set up your board exactly as you describe it.

Does this integration let me modify or delete projects?

This core integration focuses on workspace exploration, project creation, and configuration management — including workflows and labels. For task-level operations like CRUD, subtasks, and checklists, use the dedicated GitScrum Tasks integration. All actions respect your GitScrum account permissions.

GitScrum MCP Server for OpenAI Agents SDK 16 tools — connect in under 2 minutes

Name: GitScrum
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 16 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect GitScrum through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="GitScrum Assistant",
            instructions=(
                "You help users interact with GitScrum. "
                "You have access to 16 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from GitScrum"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About GitScrum MCP Server

What you can do

Browse workspaces — list all your organizational workspaces and retrieve details for each one
Manage projects — list, create, and inspect projects with full metadata including members and settings
Configure workflows — view and manage Kanban column definitions and workflow templates
Organize with labels — list, create, and update color-coded labels to categorize work
Access your profile — retrieve the authenticated user's profile across all workspaces

The OpenAI Agents SDK auto-discovers all 16 tools from GitScrum through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries GitScrum, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

The GitScrum MCP Server exposes 16 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect GitScrum to OpenAI Agents SDK via MCP

Follow these steps to integrate the GitScrum MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 16 tools from GitScrum

Why Use OpenAI Agents SDK with the GitScrum MCP Server

OpenAI Agents SDK provides unique advantages when paired with GitScrum through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

GitScrum + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the GitScrum MCP Server delivers measurable value.

Automated workflows: build agents that query GitScrum, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries GitScrum, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through GitScrum tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query GitScrum to resolve tickets, look up records, and update statuses without human intervention

GitScrum MCP Tools for OpenAI Agents SDK (16)

These 16 tools become available when you connect GitScrum to OpenAI Agents SDK via MCP:

create_project

Create a new project

create_workspace

Create a new workspace

find_project

Find a project by name

get_me

Get authenticated user profile

get_project

Get project details

get_task

Get task details by UUID

get_workspace

Get workspace details

list_labels

List labels in a project

list_project_members

List members in a project

list_projects

List projects in a workspace

list_tasks

Filter by status (todo, in-progress, done). Essential for understanding project scope and workload. List tasks in a project

list_workflows

List workflows (columns) in a project

list_workspaces

List all GitScrum workspaces

my_role

Get my role in the workspace

project_stats

Get project statistics

workspace_stats

Get workspace statistics

Example Prompts for GitScrum in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with GitScrum immediately.

"Show me all the workspaces I have access to on GitScrum."

"Create a new project called 'Mobile App v2' in the acme-eng workspace with a description."

"What labels are available in the web-app project?"

Troubleshooting GitScrum MCP Server with OpenAI Agents SDK

Common issues when connecting GitScrum to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

GitScrum + OpenAI Agents SDK FAQ

Common questions about integrating GitScrum MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.