How to Use the AfterShip Returns MCP in CrewAI

Q: How do I set up a CrewAI agent to use the AfterShip Returns tools?

It's straightforward. After pip install crewai, you can pass your Vinkius URL directly into the mcps parameter when defining your Agent. CrewAI will automatically discover and make the approvereturn and other tools available to that agent.

Q: Can different agents in a CrewAI team use different AfterShip Returns tools?

Yes. When setting up your MCP connection, you can use toolfilter to specify which tools each agent gets. For example, give your 'Monitor' agent only listreturns and your 'Action' agent only approvereturn for better security and role separation.

Q: How does a team of agents collaborate on a single AfterShip Return with CrewAI?

One agent can find a return with listreturns and pass the RMA ID to another agent via CrewAI's shared memory. The second agent can then use that ID with getreturndetails to investigate further. This is how they work together on a single task.

Deploy an autonomous crew of AI agents to manage customer returns on AfterShip 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 AfterShip Returns MCP to CrewAI

Create your Vinkius account to connect AfterShip Returns 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 AfterShip Returns with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

The Returns Processing Crew

Assign distinct roles to your agents. A 'Returns Monitor' agent can run on a schedule, using the `list_returns` tool to find new return requests. It passes any new RMAs it finds to a specialized 'Returns Analyst' agent. The Analyst agent then uses `get_return_details` to investigate each RMA—checking the items, value, and return reason. Based on its findings, it tasks an 'Action Agent' to either use `approve_return` for simple cases or flag complex ones for a human.

Autonomous Warehouse Intake

Set up a CrewAI team for your warehouse. A 'Receiving Agent' is equipped with the `receive_items` tool. When a package is scanned at the dock, this agent is triggered to log the item's arrival and condition in AfterShip. A second 'Auditor Agent' can periodically use `list_returns` with a filter for items that have been received but not yet processed. It can then create a task list for the warehouse staff, ensuring nothing falls through the cracks. This entire process runs autonomously.

Your CrewAI Financial Analyst

Create a crew to analyze the financial impact of returns. One agent, the 'Data Gatherer,' uses `list_returns` to pull all completed returns for the last quarter. It passes this raw list to the 'Details Analyst' agent. The Details Analyst iterates through the list, using `get_return_details` to find the value of the items in each return. It aggregates the total value and hands a final report to a 'Summarizer Agent,' which then sends a concise summary to the finance team via email or Slack. This MCP server provides the data access for your crew's tasks.

Setup guide

Set up AfterShip Returns 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 AfterShip Returns tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

It's straightforward. After `pip install crewai`, you can pass your Vinkius URL directly into the `mcps` parameter when defining your Agent. CrewAI will automatically discover and make the `approve_return` and other tools available to that agent.

Yes. When setting up your MCP connection, you can use `tool_filter` to specify which tools each agent gets. For example, give your 'Monitor' agent only `list_returns` and your 'Action' agent only `approve_return` for better security and role separation.

One agent can find a return with `list_returns` and pass the RMA ID to another agent via CrewAI's shared memory. The second agent can then use that ID with `get_return_details` to investigate further. This is how they work together on a single task.

Yes. You can run your crew in a loop or on a cron schedule. The 'Monitor' agent will use `list_returns` on each run to check for new RMAs, kicking off your workflow whenever a new return is detected by the system.

The server accesses customer return request data, including RMA numbers, item details, and logistics statuses from your AfterShip account. Authentication is handled by your Vinkius token, and all tool executions happen in a secure, isolated sandbox that doesn't store your 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