How to Use the Magicplan MCP in LlamaIndex

Q: How do I load Magicplan data into a LlamaIndex vector store?

You use llama-index-tools-mcp with our MCP Server. The McpToolSpec reads raw data from getprojectfloorplan and converts it into indexable document nodes for your vector database.

Q: Can LlamaIndex query specific Magicplan estimates semantically?

Yes, by indexing the output of listprojectestimates and getestimatedetails. The agent can search past financial records using natural language queries instead of exact database matches.

Q: Can I limit which tools LlamaIndex has access to?

Yes, you can use the allowedtools filter when configuring your tool specification. This allows you to restrict the agent to reading metadata via getprojectdetails while blocking financial tools.

Turn Magicplan spatial data and estimates into a searchable LlamaIndex knowledge base for RAG.

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 LlamaIndex

Create your Vinkius account to connect Magicplan to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Magicplan RAG pipelines using LlamaIndex

This MCP integration lets your LlamaIndex pipeline index spatial layouts and cost sheets directly. By using `get_project_floor_plan` and `list_project_estimates`, the framework pulls raw JSON data and converts it into document nodes for your vector store. Querying your floor plans semantically becomes straightforward once they are indexed. Instead of manually parsing dimensions, you ask your agent which rooms exceed certain parameters, and it retrieves the exact values using `get_plan_measurements` to ground its response.

Query workspace details with semantic search

This MCP Server lets you index your entire team configuration instead of searching through a database. The indexer calls `list_workspace_users` and `get_workspace_info` to build a vector representation of your current Magicplan workspace. When a query comes in about team access or workspace configurations, LlamaIndex matches the semantic intent to the indexed tools. The agent retrieves the correct user list without running expensive, custom database queries.

Ground financial estimates in real spatial data

Estimators often struggle to reconcile physical measurements with cost items. Your agent uses `get_estimate_details` alongside `get_plan_measurements` to verify that every material cost matches the actual room dimensions. By structuring this as a LlamaIndex query engine, you ensure that any generated estimate report is strictly grounded in real-world data. It eliminates the risk of hallucinated room sizes or incorrect pricing structures.

Setup guide

Set up Magicplan MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Magicplan MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Magicplan tools.",
)
response = await agent.run("List recent Magicplan data")

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 LlamaIndex

You use `llama-index-tools-mcp` with our MCP Server. The `McpToolSpec` reads raw data from `get_project_floor_plan` and converts it into indexable document nodes for your vector database.

Yes, by indexing the output of `list_project_estimates` and `get_estimate_details`. The agent can search past financial records using natural language queries instead of exact database matches.

You pass the tools retrieved from our MCP Server to the LlamaIndex `FunctionAgent`. The agent dynamically decides whether to call `get_plan_measurements` or query the vector store based on the user's question.

Yes, you can use the `allowed_tools` filter when configuring your tool specification. This allows you to restrict the agent to reading metadata via `get_project_details` while blocking financial tools.

We secure all traffic through an ephemeral V8 sandbox that isolates your data. Your workspace configurations, room dimensions, and user lists are never cached, keeping your building layouts completely private.

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