How to Use the Structured MCP in LangChain

Q: How do I search past structured plans using LangChain?

Run listplans to get all plan IDs. Your chain then passes those IDs into the next step, allowing your agent to query specific historical data for analysis.

Q: What is the best way to validate a task using Structured and LangChain?

You can use gettaskdetails first. This retrieves all metadata about an existing item, letting your agent confirm if it meets specific criteria before proceeding.

Q: Does the MCP Server support updating user data with Structured and LangChain?

Yes. While getuserprofile reads the current status, you can use this server to manage all task-related aspects of a user's routine, keeping your agent informed about changes.

Build complex planning logic with LangChain's MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Structured MCP to LangChain

Create your Vinkius account to connect Structured 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 Structured with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Orchestrate multi-step actions using the MCP Server.

Need to figure out what needs doing? Start by calling `list_plans` to get an overview of all structured plans. Then, if you want details on a specific one, hit up `get_plan_details`. This allows your agent to build a full sequence of steps based on the initial data pull.

Manage tasks and profiles with LangChain.

Your agent can check who's running the show by calling `get_user_profile` first. From there, it can list all current tasks using `list_tasks`. If a task needs changing—say, adding a due date—it runs `update_task` right away.

Control your data flow with LangChain.

This MCP Server gives you granular control over the lifecycle of tasks. You can create brand new items using `create_task`, giving it a title and an optional start time. If that task is wrong, don't sweat it; you can permanently remove it with `delete_task`.

Setup guide

Set up Structured 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 Structured 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({
    "structured-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 Structured 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 Structured. 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 Structured 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 Structured MCP in LangChain

Run `list_plans` to get all plan IDs. Your chain then passes those IDs into the next step, allowing your agent to query specific historical data for analysis.

You can use `get_task_details` first. This retrieves all metadata about an existing item, letting your agent confirm if it meets specific criteria before proceeding.

Yes. While `get_user_profile` reads the current status, you can use this server to manage all task-related aspects of a user's routine, keeping your agent informed about changes.

This MCP Server handles structured plan and task metadata. Specifically, it manages the creation and deletion of individual tasks.

Absolutely. You can chain multiple calls—like listing plans, getting details, and then creating new tasks—into one multi-step reasoning pipeline for your agent.

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