How to Use the Umbrellar MCP in CrewAI

Q: How does Umbrellar assist with CrewAI multi-agent operations?

You assign specific tools, like registerproduct, to specialized agents. The crew executes the tasks collaboratively—one agent runs the registration, and another immediately validates it using validatepolicy.

Q: How do I monitor Umbrellar policies using CrewAI?

You deploy a monitoring crew. One agent runs listpolicies to check all existing records, and another calls getpolicy on suspicious IDs for detailed review.

Deploy specialized agents for complex warranty analysis using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Umbrellar MCP to CrewAI

Create your Vinkius account to connect Umbrellar 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 Umbrellar with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Intelligent Claim Triage

Design a 'Claims Agent' that first uses `get_claim` to pull the record. A second 'Reviewer Agent' then calls `check_product_eligibility`. The final 'Action Agent' decides if it needs to submit an update using `update_claim`. This specialized crew handles complex triage: one agent researches the data, another analyzes eligibility, and a third acts on the outcome.

Autonomous Policy Management

Set up a 'Compliance Crew' to manage policies. One agent uses `list_policies` to gather all available records. A second agent then verifies them by calling `validate_policy`. The third ensures the data is current by running `sync_products`. This structure allows you to build an autonomous monitoring system for your entire policy portfolio.

Full Product Lifecycle Reporting

You can create a 'Reporting Crew' that gathers all necessary data sequentially. It first uses `list_warranties` to get plans, then calls `get_warranty` for specifics, and finally compiles the history using `list_claims`. The shared memory within the crew ensures every specialized agent has access to the full context of the product's lifecycle.

Setup guide

Set up Umbrellar 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 Umbrellar tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You assign specific tools, like `register_product`, to specialized agents. The crew executes the tasks collaboratively—one agent runs the registration, and another immediately validates it using `validate_policy`.

Yes. You can assign separate agents to different claim types. One might use `get_claim` while another focuses on listing all available claims using `list_claims`, allowing parallel investigation.

The server handles product eligibility status, policy details, and claim records. These are the core components exposed via the MCP Server for agent collaboration.

You deploy a monitoring crew. One agent runs `list_policies` to check all existing records, and another calls `get_policy` on suspicious IDs for detailed review.

Definitely. You can make a dedicated sync agent that runs the `sync_products` tool regularly, ensuring all your operational agents are working off current inventory data.

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