How to Use the GitScrum Sprints MCP in CrewAI

Q: How do I configure CrewAI agents to use GitScrum Sprints tools?

Pass your Vinkius HTTP endpoint URL directly into the mcps list when defining your CrewAI agents. This gives specialized agents instant access to MCP tools like listsprints and allsprints without requiring manual Python tool development.

Q: Does this MCP Server support selective tool exposure for CrewAI agents?

Yes, you can use the MCPServerHTTP class from crewai.mcp along with a toolfilter to restrict access. This ensures a junior developer agent can only call gettask while restricting createsprint to your manager agent.

Deploy specialized agent crews to manage GitScrum Sprints and automate backlog grooming with CrewAI.

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 CrewAI

Create your Vinkius account to connect GitScrum Sprints 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 GitScrum Sprints with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Groom backlogs using the GitScrum Sprints MCP Server

The `list_user_stories` tool pulls unassigned requirements directly from your backlog for agent review. In a CrewAI setup, a Product Owner agent analyzes these stories while a Scrum Master agent estimates their complexity. The MCP Server allows your crew to use `create_user_story` to draft refined tickets with clear acceptance criteria. This multi-agent collaboration ensures your backlog remains clean and ready for the next planning session without human intervention.

Track active sprint health with CrewAI teams

The `sprint_progress` tool monitors active ticket completion rates to identify potential delays. A monitoring agent tracks this progress hourly and coordinates with a developer agent to resolve blockers. If the crew identifies a bottleneck, it queries `list_tasks` to find the exact tickets causing the delay. The moderator agent can then update task assignments to balance the workload across the team.

Generate automated retrospective reports

The `sprint_metrics` tool compiles detailed data on team velocity, completed tasks, and missed deadlines. Your reporting crew uses this data to write detailed retrospective summaries at the end of each cycle. By analyzing `sprint_reports` and `sprint_kpis`, the agents highlight achievements and pinpoint areas for improvement. The final report is delivered directly to your team's communication channel, saving hours of manual documentation.

Setup guide

Set up GitScrum Sprints 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 GitScrum Sprints tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent GitScrum Sprints 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="GitScrum Sprints Analyst",
        goal="Access and analyze GitScrum Sprints data via MCP.",
        backstory="Expert analyst with direct GitScrum Sprints access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent GitScrum Sprints 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 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 CrewAI

Pass your Vinkius HTTP endpoint URL directly into the `mcps` list when defining your CrewAI agents. This gives specialized agents instant access to MCP tools like `list_sprints` and `all_sprints` without requiring manual Python tool development.

Yes, your agents share a common memory space and can execute sequential or hierarchical tasks. For instance, one agent can fetch tasks using `list_tasks` while another updates their status using `update_sprint` based on the analysis.

Yes, you can use the `MCPServerHTTP` class from `crewai.mcp` along with a `tool_filter` to restrict access. This ensures a junior developer agent can only call `get_task` while restricting `create_sprint` to your manager agent.

The MCP Server implements a localized caching strategy for heavy read operations like `sprint_stats` and `list_epics`. This prevents your agent crews from exhausting your GitScrum API limits during intensive planning loops.

Your sprint metrics, task descriptions, and user story details are processed live inside secure, ephemeral sandboxes. Vinkius acts as a secure proxy, executing the tools and passing the results directly to your local CrewAI environment without storing any project data.

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