How to Use the GitScrum Tasks MCP in AutoGen

Q: How do I register the GitScrum Tasks MCP Server with AutoGen?

Install the autogen-ext package and use the mcpservertools utility. Pass the Vinkius server URL to configure the adapter, then register the returned tools with your AssistantAgent.

Q: Can AutoGen agents debate task priorities before assigning them on GitScrum Tasks?

Yes, one agent can fetch priority levels using listeffortlevels while another evaluates the workload. They can then agree on an estimate and call settaskestimate to update the task.

Q: How do AutoGen agents handle subtask creation on GitScrum Tasks?

An agent can create a task using createtask, and another agent can verify it and call linksubtask to chain it to a parent task, ensuring hierarchical organization.

Q: Can my agents delete tasks if they are duplicates?

Yes, your agents can use duplicatetask to clone tasks, or use deletetask to permanently remove redundant items once they reach consensus.

Enable multi-agent debate and consensus over your GitScrum board to automate complex project management workflows using this dedicated MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GitScrum Tasks MCP to AutoGen

Create your Vinkius account to connect GitScrum Tasks to AutoGen 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 Tasks with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents collaborate on GitScrum Tasks

This MCP Server allows your AutoGen agents to coordinate task management using tools like `create_task` and `assign_member`. A planning agent can draft a new task, while a quality assurance agent reviews the requirements and uses `update_task` to refine the acceptance criteria before work begins. By dividing responsibilities, one agent can run `list_task_types` to find the correct classification while another executes `create_task_type` with specific hex codes. This prevents single-agent errors and keeps your board clean.

Resolve dependencies and blockers through agent debate

The `related_tasks` tool helps your agents identify task dependencies and flag potential bottlenecks. If a blocker is found, a coordinator agent can use `list_tasks` to find the owner, then invoke `create_comment` to notify them of the dependency. When conflicts are resolved, the agents use `toggle_task_done` to update the task status. This entire negotiation happens autonomously, with agents challenging each other's updates to ensure accuracy.

Automate daily standups and task assignments

The `my_today_tasks` tool lets your agents scan for tasks due today and assign them to the correct team members. If a team member is overloaded, the agent can use `unassign_member` and then call `assign_member` to reallocate the work to someone else. Agents can also compile progress reports by querying `list_checklists` and posting updates. They use `update_comment` to keep team members informed of changes without manual intervention.

Setup guide

Set up GitScrum Tasks MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes GitScrum Tasks tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="GitScrum Tasks_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent GitScrum Tasks data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="GitScrum Tasks_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent GitScrum Tasks data")
    print(result.messages[-1].content)

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 Tasks 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 Tasks MCP in AutoGen

Install the autogen-ext package and use the mcp_server_tools utility. Pass the Vinkius server URL to configure the adapter, then register the returned tools with your AssistantAgent.

Yes, one agent can fetch priority levels using `list_effort_levels` while another evaluates the workload. They can then agree on an estimate and call `set_task_estimate` to update the task.

An agent can create a task using `create_task`, and another agent can verify it and call `link_subtask` to chain it to a parent task, ensuring hierarchical organization.

Yes, your agents can use `duplicate_task` to clone tasks, or use `delete_task` to permanently remove redundant items once they reach consensus.

All interactions with your tasks, stories, and checklists are routed through secure, zero-trust Vinkius endpoints. No agent conversation data or GitScrum authentication keys are stored or exposed to external networks.

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