How to Use the ONES MCP in LangChain

Q: How does LangChain handle complex workflow transitions in ONES?

Your agent uses listworkflows to inspect valid transitions first. This prevents the model from attempting an invalid updatetask call that would fail platform schema validation rules.

Q: How does the ONES LangChain integration protect our member lists?

Vinkius isolates all requests to listmembers inside a secure V8 sandbox on our managed MCP platform. Your organization directory and member UUIDs never persist on external servers, keeping your HR data locked down.

Build LangChain agents that inspect ONES project workflows, assign tasks, and write updates in a single execution chain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect ONES MCP to LangChain

Create your Vinkius account to connect ONES to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup ONES with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain ONES Workflow Queries inside LangChain

`list_workflows` is the tool that lets your LangChain agent pull active engineering states directly into a ReAct execution loop using this MCP server. The LangChain model maps these transitions to current ticket statuses and routes the output to the next chain link without human intervention.

Automate Task Creation with Multi-Step Reasoning

`create_task` runs as a downstream step in your LangChain pipeline once the model verifies project details. This multi-step adapter setup prevents orphaned tickets by forcing the LangChain chain to validate the ONES project destination.

Map Teams to Tasks with LangChain Context

`list_members` allows your LangChain agent to inspect your team roster before assigning work. By handling these assignments in a single stateless LangChain session, your pipeline avoids hardcoding developer IDs inside ONES.

Setup guide

Set up ONES 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 ONES 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({
    "ones-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 ONES 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 ONES. 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 ONES 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 ONES MCP in LangChain

Yes, you can track every execution. LangSmith logs each call to list_tasks or get_task_details so you can verify the agent's reasoning path and monitor API token usage.

Use the MultiServerMCPClient to combine this service with your database tools. The LangChain agent can fetch a bug report from your database, query list_task_types to find the correct format, and then call create_task in a single run using the MCP protocol.

It does. The adapter runs stateless queries by default, but you can open a persistent context session if your agent needs to retain get_project details across multiple chat turns.

Your agent uses list_workflows to inspect valid transitions first. This prevents the model from attempting an invalid update_task call that would fail platform schema validation rules.

Vinkius isolates all requests to list_members inside a secure V8 sandbox on our managed MCP platform. Your organization directory and member UUIDs never persist on external servers, keeping your HR data locked down.

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