How to Use the Nestoria MCP in CrewAI

Q: How do I give only one agent in my CrewAI team access to the Nestoria search tool?

When defining your agents, only include the searchlistings tool in the tools list for the specific agent you want to act as the scout. This ensures role-based specialization within your crew.

Assemble a crew of autonomous agents with CrewAI to find, analyze, and report on Nestoria real estate listings.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nestoria MCP to CrewAI

Create your Vinkius account to connect Nestoria 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 Nestoria with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign a Dedicated Real Estate Scout

The `search_listings` tool gives an agent the ability to search Nestoria's global property database. It's a simple, powerful operation for finding homes to buy or rent. In CrewAI, you don't give this tool to every agent. You create a specialized 'Real Estate Scout' agent and assign `search_listings` as its only tool. This agent's entire job is to execute searches, keeping your crew organized and efficient.

Create Collaborative Real Estate Teams

A scout finds the properties, but who analyzes them? That's the power of CrewAI. Your Scout Agent uses `search_listings` to get a raw list of 100 properties. It then passes that list to an 'Analyst Agent' who filters, sorts, and finds the top 5 investment opportunities. Because all agents in a crew can share context, the Analyst knows exactly what the Scout was looking for. A final 'Reporter Agent' can then take the top 5 list and write a summary. This is how you automate complex research tasks with this MCP server.

Simple Setup for Autonomous Crews

Connecting your crew is easy. Just add the Vinkius MCP endpoint URL to your agent's `mcps` list in the CrewAI setup. For more control, you can use `MCPServerHTTP` and a `tool_filter` to ensure only specific agents can access the `search_listings` tool. Once configured, your crew runs autonomously. You can kick off a task to find 'the best starter homes in Portugal' and the agents will collaborate, using Nestoria's data to deliver a final report without any further input.

Setup guide

Set up Nestoria 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 Nestoria tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Nestoria 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="Nestoria Analyst",
        goal="Access and analyze Nestoria data via MCP.",
        backstory="Expert analyst with direct Nestoria access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Nestoria 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 Nestoria. 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 Nestoria 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 Nestoria MCP in CrewAI

When defining your agents, only include the `search_listings` tool in the `tools` list for the specific agent you want to act as the scout. This ensures role-based specialization within your crew.

Yes, that's a core feature of CrewAI. An agent can execute a task using `search_listings` and its output (the list of properties) becomes part of the shared context, which other agents can then access for their own tasks.

You define that in the task you give the agent. For example, your task description might be: 'Search for rental properties in Germany under €1000/month.' The agent will parse this and use 'Germany' as the country parameter for the `search_listings` tool.

No. The MCP server is a pass-through. It receives a request from your agent to execute a tool and sends back the result. The broader context of your crew's tasks and goals is not visible to the server.

The only data processed is the immediate search query itself, like the target country and price range. These property search details are sent to the Nestoria API via our ephemeral server; the data exists only for the lifetime of the request and is not stored or analyzed.

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