How to Use the Wing Assistant MCP in LangChain

Q: Can I track task status using Wing Assistant and LangChain?

Yeah, you use the gettaskstatus tool. Your chain can poll this endpoint repeatedly to know exactly when a unit of work is done or if it stalled out.

Build complex workflows with Wing Assistant and LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wing Assistant MCP to LangChain

Create your Vinkius account to connect Wing Assistant 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 Wing Assistant with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Building Chains with the MCP Server

You can link multiple operations into a single execution flow. For instance, your agent calls `list_assistants` to get names, then uses those names as inputs for calling `get_task_status`. This creates a verifiable chain of actions. The output from one tool call immediately becomes the input for the next step in your LangChain graph. You're not just running tools; you're building reasoning pipelines where the agent decides what to do and when.

Managing Tasks with Wing Assistant

Need to delegate work? The `create_task` tool lets your multi-step agent assign a specific title and description. Your chain can then immediately follow up by calling `update_task` if the initial assignment needs tweaking. It’s ideal for automated workflows where one step is initiating work, and the next steps are monitoring or adjusting that work based on the task ID.

Observability via LangSmith Tracing

Debugging complex logic is simple because of full observability. LangSmith traces capture everything: which tool was called, what data went in, and what came out. You can even see the latency and token usage for every single step. This detailed logging means you're building reliable agents. You know exactly why your agent decided to call `get_task_status` before checking `list_tasks`; there’s no guesswork involved.

Setup guide

Set up Wing Assistant 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 Wing Assistant 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({
    "wing-assistant-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 Wing Assistant 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 Wing Assistant. 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 Wing Assistant 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 Wing Assistant MCP in LangChain

The MCP Server exposes the assistant's tools as links in your chain. Your agent decides which tool to call and what order to run them in, making it part of a larger reasoning pipeline.

Yeah, you use the `get_task_status` tool. Your chain can poll this endpoint repeatedly to know exactly when a unit of work is done or if it stalled out.

Absolutely. Since the MCP Server output is just another data point, you can pass it to databases or vector stores alongside your tool outputs. It's treated like any other piece of data.

This server manages task records, including titles, descriptions, and the current status associated with specific virtual assistants.

It lets you build sophisticated agents that don't just run one function. They can reason—they check a list of assistants, create a task, and then monitor the status, all in sequence.

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