How to Use the Hostfully MCP in CrewAI

Q: Can I filter Hostfully tools for specific CrewAI agents?

Yes. Use MCPServerHTTP from crewai.mcp and apply a toolfilter. You don't want your guest-facing agent accessing owner financials through the MCP server.

Q: How does CrewAI handle sensitive Hostfully lead contact info?

Agents access raw emails and phone numbers through getlead. The Vinkius infrastructure processes this personal data entirely in memory, destroying the container immediately after the Python script receives the payload.

Deploy a CrewAI autonomous team to run your Hostfully vacation rentals. Let specialized Python agents handle guests and maintenance.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hostfully MCP to CrewAI

Create your Vinkius account to connect Hostfully 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 Hostfully with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous guest relations

The Hostfully MCP server turns your CrewAI setup into a fully staffed digital property management company. You assign specific endpoints to different AI personas. You create a Guest Relations Agent and give it access to `list_guests` and `list_leads`. When an inquiry comes in, this agent reads the reservation details, drafts a personalized response, and flags high-value bookings for human review.

Maintenance dispatch crew

Property management requires coordinating multiple moving parts. A single agent gets confused, but a hierarchical crew thrives here. Your Monitor Agent watches for checkout events using `list_properties`. It then passes the property ID to your Dispatch Agent, which uses `list_service_providers` to find local plumbers or cleaners and send them work orders. This MCP architecture ensures tools stay scoped.

Agency oversight and reporting

Tracking performance across hundreds of listings requires constant auditing. You can set up a background crew to run daily checks. A Reporting Agent calls `list_agencies` to pull the active roster, then loops through `list_owners` to generate individual performance summaries. This MCP server compiles the data and sends a nightly Slack message to your human team.

Setup guide

Set up Hostfully 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 Hostfully tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass the endpoint URL directly into your Agent configuration using mcps=["https://..."]. CrewAI automatically discovers and maps the available tools.

Yes. Use MCPServerHTTP from crewai.mcp and apply a tool_filter. You don't want your guest-facing agent accessing owner financials through the MCP server.

They share memory within the same execution sequence. The agent that pulls the lead data passes the exact JSON context to the agent writing the email.

You connect to the managed Vinkius endpoint. Your Python scripts run locally, but the API requests route through the isolated cloud sandbox.

Agents access raw emails and phone numbers through get_lead. The Vinkius infrastructure processes this personal data entirely in memory, destroying the container immediately after the Python script receives the payload.

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