How to Use the VivifyScrum MCP in CrewAI

Q: What is the best way to track VivifyScrum progress using CrewAI?

Use a dedicated 'Tracker' agent. It can call listsprints and then loop through results from getboard to provide a summarized status report on active timeboxes.

Run Autonomous Agile Operations with CrewAI Multi-Agent Teams.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect VivifyScrum MCP to CrewAI

Create your Vinkius account to connect VivifyScrum to CrewAI 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 VivifyScrum with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map the Entire Project Landscape

You can assign one agent to run `list_teams` and another to execute `list_boards`. The agents then share memory, allowing a third agent to compare them and report any discrepancies. This setup is ideal for an initial audit where multiple specialized roles need to gather foundational context.

Analyze Work History Across Boards

One agent pulls all item listings using `list_board_items`, while a second agent concurrently calls `get_worklogs` for deeper analysis. The monitor agent then cross-references the two data streams. This gives you a complete picture: what was planned versus what actually happened, based on historical work.

Automate Item Lifecycle Management

A 'Creator' agent runs `create_item` to draft new stories. Later, an 'Executor' agent uses `update_item` to change the status once the story is ready for review. This sequential execution simulates a full development sprint cycle entirely without human intervention.

Setup guide

Set up VivifyScrum MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke VivifyScrum tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="VivifyScrum Analyst",
    goal="Access and analyze VivifyScrum data via MCP.",
    backstory="Expert analyst with direct VivifyScrum access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent VivifyScrum transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="VivifyScrum Analyst",
        goal="Access and analyze VivifyScrum data via MCP.",
        backstory="Expert analyst with direct VivifyScrum access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent VivifyScrum transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 VivifyScrum. 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 VivifyScrum 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 VivifyScrum MCP in CrewAI

You pass the MCP endpoint URL directly to your agents. The crew then uses tools like `list_organizations` and `get_account_info` to establish context, ensuring all subsequent tasks are scoped correctly.

Use a dedicated 'Tracker' agent. It can call `list_sprints` and then loop through results from `get_board` to provide a summarized status report on active timeboxes.

Yes. You can define roles like 'Project Manager' (who lists boards) and 'Developer' (who updates items). Their shared memory enables a multi-step, autonomous operation.

The server exposes tools for everything from listing teams (`list_teams`) to managing webhooks (`list_webhooks`). You select the specific tools your agents need, keeping the operation focused.

The server handles project metadata, including board names, task descriptions, worklogs, and organizational details. It doesn't interact with financial or personal identity records.

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