How to Use the GitScrum MCP in LangChain

Q: How do I pass GitScrum MCP tools to a LangChain agent?

Install langchain-mcp-adapters and use MultiServerMCPClient to connect to the Vinkius endpoint. Call gettools() on the client and pass the resulting tool list directly to your LangChain agent constructor.

Q: Can LangChain run multi-step chains using GitScrum data?

Yes, ReAct agents can feed the output of listworkspaces into listprojects sequentially. LangChain manages the state between these tool calls automatically.

Q: How does LangSmith trace GitScrum tools inside LangChain?

LangSmith captures all inputs and outputs for tools like gettask and projectstats executed through the MCP adapter. You get full visibility into latency and token usage for each board query.

Build LangChain agents that spin up GitScrum projects and audit workspace tasks without leaving your terminal.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GitScrum MCP to LangChain

Create your Vinkius account to connect GitScrum 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 with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain-linked project setup and workspace provisioning

The GitScrum MCP Server exposes `create_workspace` and `create_project` directly to your LangChain ReAct agents. Your agent takes a raw product spec, spins up a workspace, builds the project, and maps out workflows in a single execution chain. You can trace this entire sequence using LangSmith to see exactly how your chain resolved the project metadata. The output of `create_workspace` flows directly into `create_project` without manual data passing.

Multi-step task auditing with LangChain and MCP

This integration hooks `list_tasks` and `list_workflows` into your LangChain pipelines to automate board hygiene. Your agent queries the active board columns, finds stalled tasks, and flags them for review. Because LangChain handles multi-server aggregation, you can merge this task inspection with your external databases. The agent runs `get_task` to pull details and verifies them against your production telemetry.

Context-aware team role verification

Use `my_role` and `list_project_members` inside your conversational chains via our MCP Server to enforce project boundaries. LangChain agents query these tools to determine who has permission to modify board structures. This setup ensures your agent never attempts to run write operations for unauthorized users. The LLM checks the workspace role before executing any updates on active tasks.

Setup guide

Set up GitScrum 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 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-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 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 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 MCP in LangChain

Install `langchain-mcp-adapters` and use `MultiServerMCPClient` to connect to the Vinkius endpoint. Call `get_tools()` on the client and pass the resulting tool list directly to your LangChain agent constructor.

Yes, ReAct agents can feed the output of `list_workspaces` into `list_projects` sequentially. LangChain manages the state between these tool calls automatically.

LangSmith captures all inputs and outputs for tools like `get_task` and `project_stats` executed through the MCP adapter. You get full visibility into latency and token usage for each board query.

Absolutely. LangChain supports over 500 integrations, letting you chain GitScrum board updates with SQL databases or vector stores in a single agent session.

All task details and workspace configurations remain inside the V8 isolate sandbox on Vinkius. Your credentials never leak to the LLM, and data is only fetched on demand during active runs.

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