How to Use the Upzelo MCP in CrewAI

Q: Can I get customer details in real-time using Upzelo and CrewAI?

Absolutely. You assign the task of retrieving data using getcustomer. The agent executes this tool, retrieves the details, and passes them to the next agent for analysis.

Orchestrate specialized teams to manage customer retention with CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Upzelo MCP to CrewAI

Create your Vinkius account to connect Upzelo 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 Upzelo with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative Customer Data Gathering

Imagine a team: Agent A gathers the list of users using `list_customers`. Then, Agent B takes that raw data and uses it to find specific details for each one with `get_customer`. The shared memory between agents makes this possible. Agent B doesn't need you to manually pass the IDs; it just knows who Agent A found.

Automated Retention Flow Management

You can define a process where one agent checks campaign readiness using `list_flows`. Then, another specialized agent initiates the campaign via `start_flow`. This is autonomous operation. The agents manage the handoff from checking data to executing the flow without any human intervention.

Executing Multi-Step Subscription Changes

One agent can be assigned the role of 'Billing Specialist.' This specialist uses `update_subscription` to change attributes. If the update needs a customer ID, another agent retrieves it using `get_customer` first. The agents collaborate sequentially: research (A), analyze/retrieve data (B), and act (C).

Setup guide

Set up Upzelo 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 Upzelo tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You assign roles to your agents. One agent can be responsible for running `list_customers`, and another specialized agent uses that output to call `save_customer` for segmentation.

Yes. You set up a process where an initial agent checks flow details with `get_flow`, and a subsequent agent executes the campaign by calling `start_flow`.

This MCP Server handles customer records and subscription attributes, specifically touching **customer details** and **subscription attributes**. The agents treat this data as shared memory for their task execution.

The crew structure ensures reliability. One agent can pull the full list using `list_subscriptions`, and a second agent can then use that information to verify specific details via `get_subscription`.

Absolutely. You assign the task of retrieving data using `get_customer`. The agent executes this tool, retrieves the details, and passes them to the next agent for analysis.

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