How to Use the Zuplo MCP in CrewAI

Q: How does Zuplo help with deployments using CrewAI?

The 'Deployment Agent' calls createdeployment, and the monitoring agent uses listdeployments to confirm status. The whole process is observable, allowing for automated retries on failure.

Q: Can I list Zuplo projects with CrewAI?

Yes. The 'Discovery Agent' runs listprojects as a core task. This provides the foundational scope needed before any other operations, like checking consumer lists, can begin.

Q: Does Zuplo let me see all environments with CrewAI?

The agent uses listenvironments to determine the scope of a project, checking if 'production' or other necessary deployment targets exist. This is critical for autonomous execution.

Q: If I need metrics for Zuplo using CrewAI, what tool do I use?

The 'Analysis Agent' calls getmetrics. It takes the resulting performance data and stores it in shared memory, allowing other agents to act on that insight.

Build autonomous operational crews using CrewAI with Zuplo API management tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Zuplo MCP to CrewAI

Create your Vinkius account to connect Zuplo 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 Zuplo with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit and Control Consumers

To audit who has access, the `list_consumers` tool reports all active API key consumers. If a new client signs up during an operation, the 'Onboarding' agent can use `create_consumer`. The 'Cleanup' agent handles decommissioned accounts by running `delete_consumer`, ensuring no orphaned credentials remain.

Deploy and Track API Gateways

The 'Deployment Agent' starts new services using `create_deployment`. After deployment, the system needs status updates; use `list_deployments` to check which versions are active. The agent also uses `get_metrics` to collect performance data for the newly deployed API gateway, feeding it into the shared memory.

Map Zuplo Infrastructure

The 'Discovery Agent' runs `list_projects` to establish a baseline map of all available Zuplo projects. From there, it uses `list_environments` and `list_custom_domains` to fully characterize the deployment target. Finally, running `list_files` helps locate specific configuration files needed for advanced setup tasks.

Setup guide

Set up Zuplo 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 Zuplo tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

The 'Deployment Agent' calls `create_deployment`, and the monitoring agent uses `list_deployments` to confirm status. The whole process is observable, allowing for automated retries on failure.

Yes. The 'Discovery Agent' runs `list_projects` as a core task. This provides the foundational scope needed before any other operations, like checking consumer lists, can begin.

This server handles API key consumer information, which involves highly sensitive credentials like API keys. The 'Moderator Agent' should always verify the required scopes before calling `list_consumers`.

The agent uses `list_environments` to determine the scope of a project, checking if 'production' or other necessary deployment targets exist. This is critical for autonomous execution.

The 'Analysis Agent' calls `get_metrics`. It takes the resulting performance data and stores it in shared memory, allowing other agents to act on that insight.

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