How to Use the GitScrum Tasks MCP in LangChain

Q: Can my LangChain agent update task estimates on GitScrum Tasks?

Yes, the agent can use the settaskestimate tool to update story points. It can also read current priority levels using listeffortlevels before making changes.

Q: How does GitScrum Tasks handle subtask linking inside a LangChain chain?

Your agent can call createtask to get a new task's details, then immediately pass that ID to linksubtask to link it to an existing parent task. This happens in a single execution loop.

Q: Can I filter tasks by specific team members?

Yes, you can use listtasks with the users filter to find items assigned to specific people, or run mytasks to get work assigned to the active user.

Get your LangChain agents managing your sprint board directly through multi-step reasoning chains with this 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 LangChain

Create your Vinkius account to connect GitScrum Tasks to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step GitScrum task chains in LangChain

This MCP Server exposes `create_task` and `link_subtask` directly to your LangChain ReAct agents. The output from one tool call feeds straight into the next, allowing your pipeline to initialize a parent epic and instantly chain a dozen child tasks without manual intervention. Your agent evaluates the output of `list_task_types` to select the correct hex color code, then executes `create_task_type` before organizing the backlog. LangSmith traces every tool call, giving you full visibility into latency and token usage for every task created.

Filter and assign sprint workloads automatically

The `list_tasks` tool lets your agent query your active board using advanced parameters like sprint, status, and user story. From there, the agent can loop through unassigned items and invoke `assign_member` to balance the workload across your team based on real-time availability. You can also run `my_today_tasks` to fetch urgent items and immediately trigger `set_task_estimate` to update story points. This keeps your sprint metrics accurate without developers wasting time on manual entry.

Maintain clean task histories and checklists

The `create_checklist_item` tool gives your LangChain agent the ability to break down complex tasks into atomic action items. If an acceptance criterion changes, the agent runs `toggle_checklist_item` to update the state or appends context using `create_comment` with rich text support. When cleanup is required, the agent uses `delete_comment` or `unlink_subtask` to keep the project board tidy. Every change is logged in your tracing pipeline, ensuring you can debug agent decisions instantly.

Setup guide

Set up GitScrum Tasks MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes GitScrum Tasks tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "gitscrum-tasks-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent GitScrum Tasks transactions"
    })
    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 LangChain

Install the adapter package using pip and initialize the client. You can use the MultiServerMCPClient with the HTTP transport pointing to your Vinkius endpoint, then pass the tools directly to your agent executor.

Yes, the agent can use the `set_task_estimate` tool to update story points. It can also read current priority levels using `list_effort_levels` before making changes.

Your agent can call `create_task` to get a new task's details, then immediately pass that ID to `link_subtask` to link it to an existing parent task. This happens in a single execution loop.

Yes, you can use `list_tasks` with the users filter to find items assigned to specific people, or run `my_tasks` to get work assigned to the active user.

All task details, comments, and checklist items are sent through an isolated Vinkius sandbox via this MCP Server. Your GitScrum credentials are encrypted, ensuring your private task descriptions and team assignments never leak to public models.

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