How to Use the Magicplan MCP in LangChain

Q: How do I pass Magicplan tool outputs directly to a LangChain agent?

You install langchain-mcp-adapters and use the MultiServerMCPClient to connect to our hosted MCP endpoint. Once connected, call client.gettools() and pass those tools directly to your agent's constructor so it can run tools like getprojectdetails on demand.

Build multi-step LangChain pipelines that pull spatial data and write estimates without leaving your runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Magicplan MCP to LangChain

Create your Vinkius account to connect Magicplan 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 Magicplan with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-step floor plan analysis with LangChain

Your LangChain agent can now chain spatial data requests directly into financial calculations. By calling `get_project_floor_plan` to inspect the layout, the agent passes those dimensions directly into `list_project_estimates` to check budget alignment. This chain runs without manual intervention, turning complex spatial queries into a single execution path. You track every single tool call in LangSmith, which shows you exactly how the agent navigated from `get_project_details` to the final floor plan output. If the agent gets stuck or grabs the wrong layout, you see the exact payload and can tweak your prompt templates instantly.

Map workspace users to specific project estimates

Managing access and budgets across real estate projects is messy when done manually. This MCP Server lets your LangChain agent query `list_workspace_users` to see who is on site, then immediately run `get_estimate_details` to audit their specific financial drafts. The agent handles this by passing variables through a structured chain, ensuring that user IDs from one tool feed straight into the parameters of the next. It avoids the need to write custom glue code for every Magicplan API endpoint.

Extract custom form data during LangChain runs

Field technicians fill out custom checklists on site, and your LangChain agent needs that raw data to make decisions. The agent calls `list_available_forms` to find the correct checklist template, then triggers `get_plan_form_data` to pull the actual values from the active plan. This MCP capability allows you to construct decision-making nodes in LangGraph where the agent's next action depends entirely on whether a form field is marked complete. You get a deterministic pipeline that still adapts to real-world floor plan updates.

Setup guide

Set up Magicplan 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 Magicplan 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({
    "magicplan-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 Magicplan 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 Magicplan. 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 Magicplan 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 Magicplan MCP in LangChain

You install `langchain-mcp-adapters` and use the `MultiServerMCPClient` to connect to our hosted MCP endpoint. Once connected, call `client.get_tools()` and pass those tools directly to your agent's constructor so it can run tools like `get_project_details` on demand.

Yes, you do this through LangSmith. Every time your LangChain agent calls `get_plan_measurements` or `get_project_floor_plan`, the latency, token count, and exact spatial payloads are logged in your tracing dashboard.

Absolutely. You can combine this server with a database or email server inside a single LangChain `MultiServerMCPClient`. This lets your agent pull room dimensions with `get_plan_measurements` and write them directly to an external database in one run.

By default, the adapter handles tools statelessly. If your agent needs to keep track of a specific project ID across multiple steps, you should manage that state inside your LangGraph state schema or use `client.session()` to keep context alive.

We run the server in a secure, ephemeral V8 Isolate sandbox that has zero-trust access. Your API keys, spatial measurements, and financial estimates are never stored on our servers, and we handle all authentication via a single secure token.

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