How to Use the Magicplan MCP in CrewAI

Q: How do I inject Magicplan tools into CrewAI?

Pass your Vinkius HTTP transport URL directly into the mcps array when defining your agent. CrewAI connects to the MCP server and registers the tools automatically.

Q: Can multiple CrewAI agents share Magicplan project data?

Yes. Your researcher agent can call getworkspaceinfo and store the result in shared memory. The rest of the crew reads that context to inform their subsequent actions.

Q: How do I restrict which Magicplan tools a CrewAI agent uses?

Use MCPServerHTTP from crewai.mcp and apply a toolfilter. You can limit your junior agent to listavailableforms while reserving the financial endpoints for the senior auditor.

Deploy specialized real estate agents. Hook this Magicplan MCP Server into CrewAI to let autonomous teams audit project costs.

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 CrewAI

Create your Vinkius account to connect Magicplan to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Project Auditing

The `list_magicplan_projects` tool pulls the entire directory of active property scans. You assign this to a designated Researcher agent in CrewAI. This agent monitors the workspace continuously, looking for newly uploaded properties that need review. Once it finds a new entry, it passes the ID to the Analyzer agent. This second agent calls `get_project_details` to read the metadata. The crew shares this context in memory, allowing them to collaborate on the audit without waiting for a human to trigger the next step.

Magicplan MCP Server Spatial Analysis

The `get_project_floor_plan` tool extracts the exact wall coordinates and room layouts. Your CrewAI spatial specialist takes this data and evaluates the building footprint. It cross-references the layout against local zoning rules stored in its prompt. The agent then fires `get_plan_measurements` to pull the raw square footage. It compares the visual floor plan against the hard numeric data to spot discrepancies. If the numbers clash, the moderator agent escalates the issue to a human architect.

Multi-Agent Financial Reviews

The `list_project_estimates` tool retrieves every draft quote attached to a property. You give this capability to a dedicated Estimator agent. It scans the list and identifies which quotes still sit in a draft state. It hands the draft IDs off to an Auditor agent that runs `get_estimate_details`. The Auditor reads the specific material and labor costs. It checks the pricing against a master database and automatically flags overpriced line items in a final report.

Setup guide

Set up Magicplan MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Magicplan tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Magicplan Analyst",
    goal="Access and analyze Magicplan data via MCP.",
    backstory="Expert analyst with direct Magicplan access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Magicplan transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Magicplan Analyst",
        goal="Access and analyze Magicplan data via MCP.",
        backstory="Expert analyst with direct Magicplan access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Magicplan transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass your Vinkius HTTP transport URL directly into the `mcps` array when defining your agent. CrewAI connects to the MCP server and registers the tools automatically.

Yes. Your researcher agent can call `get_workspace_info` and store the result in shared memory. The rest of the crew reads that context to inform their subsequent actions.

Use `MCPServerHTTP` from `crewai.mcp` and apply a `tool_filter`. You can limit your junior agent to `list_available_forms` while reserving the financial endpoints for the senior auditor.

No. Vinkius manages the underlying auth. You provide a single endpoint token to the framework. The agents just call the tools without worrying about token expiration.

Your precise wall coordinates and room measurements execute inside a V8 Isolate Sandbox. Vinkius spins up an ephemeral instance for the request. The environment terminates immediately after returning the spatial data to CrewAI.

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