How to Use the Cardly MCP in CrewAI

Q: How do I configure Cardly in CrewAI?

Install crewaitools and pass your Vinkius endpoint URL directly into the mcps array on your agent definition.

Deploy autonomous CrewAI teams that research clients and mail personalized physical greeting cards via this Cardly MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cardly MCP to CrewAI

Create your Vinkius account to connect Cardly 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 Cardly with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Research and Mailing

One agent shouldn't handle both researching a prospect and shipping them a physical gift. Splitting these tasks across specialized roles prevents hallucinations from ruining a real-world mailing. You assign a researcher agent to draft the perfect message based on scraped data. A separate fulfillment agent then takes that drafted text and executes `place_greeting_card_order` to actually mail the physical card.

Filter Cardly Tools for CrewAI

Giving a single agent access to every greeting card endpoint is dangerous. You do not want your drafting agent accidentally firing off a batch of expensive orders. Using MCPServerHTTP from crewai.mcp, you apply a tool_filter to restrict access. Give the designer agent access to `list_card_artwork` and `preview_greeting_card`, while strictly reserving the order tools for your manager agent.

Audit Physical Mail Spend

Keeping track of autonomous spending requires dedicated oversight. Teams that send physical mail need a monitor watching the budget constantly. Spin up an auditor agent that periodically runs `get_account_info` to check your remaining balance. If the funds drop below a threshold, it alerts your slack channel before the fulfillment agents hit order failures.

Setup guide

Set up Cardly 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 Cardly tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install crewai[tools] and pass your Vinkius endpoint URL directly into the mcps array on your agent definition.

Yes. You define the MCP Server once and assign it to multiple agents, or restrict specific tools to individual agents using a filter.

Agents use their shared memory to understand when an order fails. They read the error from the MCP Server and attempt to correct the payload before trying again.

The framework supports stdio, SSE, and Streamable HTTP. For remote Vinkius endpoints, Streamable HTTP provides the most stable connection.

The system processes physical mailing addresses and personal messages purely in-memory. Every MCP Server runs within an ephemeral sandbox that destroys the data as soon as the agent completes the task.

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