How to Use the Amazon Selling Partner MCP in CrewAI

Q: How do I connect the Amazon Selling Partner MCP Server to CrewAI?

Install crewaitools. You can pass the Vinkius URL directly into your agent's definition using mcps="YOURVINKIUSURL". The framework handles the HTTP transport automatically.

Q: Can I restrict which Amazon Selling Partner tools my CrewAI agents can use?

Yes. For advanced setups, import MCPServerHTTP from crewai.mcp. You can apply a toolfilter so your Analyst Agent only accesses listfinancialevents while your Inventory Agent only sees listfbainventory.

Q: How does CrewAI handle long-running Amazon Selling Partner reports?

Your agents can operate sequentially. One agent triggers createreport, and a separate Monitor Agent runs in a loop checking getreportstatus until the file is ready for analysis.

Deploy an autonomous CrewAI team to run your Amazon operations. Assign specific agents to monitor FBA inventory and manage orders.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazon Selling Partner MCP to CrewAI

Create your Vinkius account to connect Amazon Selling Partner 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 Amazon Selling Partner with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Hierarchical FBA Crews

Managing a massive Amazon catalog and FBA inventory requires more than a single agent. CrewAI lets you connect this MCP Server to a strict hierarchy where a Manager Agent oversees a specialized Inventory Agent. The Inventory Agent fires `list_fba_inventory` every hour to check warehouse levels across the country. When stock dips, the Inventory Agent writes a summary into shared memory. A secondary Procurement Agent reads that memory, uses `get_catalog_item` to pull the exact ASIN details, and drafts a supplier restock order without human intervention.

CrewAI Financial Audit Teams

Stop manually reconciling Amazon payouts and financial events. You can configure a CrewAI team dedicated entirely to accounting. The Auditor Agent runs `list_financial_events` to pull all recent fees, refunds, and adjustments into the session context. If the numbers look wrong, the Auditor triggers a secondary Analyst Agent. The Analyst executes `create_report` to request the massive GET_MERCHANT_LISTINGS_ALL_DATA file, periodically checks `get_report_status`, and parses the final CSV to find exactly where the discrepancies occurred.

Autonomous Order MCP Server

Resolving customer support tickets scales poorly when humans have to cross-reference multiple Amazon order dashboards. Build a sequential CrewAI pipeline instead. The Triage Agent reads an incoming complaint and immediately runs `list_orders` to find the buyer's history. It passes the exact order ID to the Resolution Agent, which calls `get_order_items` to verify exactly what shipped. Because CrewAI agents share context, the final Communications Agent drafts a highly specific apology or tracking update based on the raw Amazon data.

Setup guide

Set up Amazon Selling Partner 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 Amazon Selling Partner tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Amazon Selling Partner 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 Amazon Selling Partner. 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 Amazon Selling Partner 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 Amazon Selling Partner MCP in CrewAI

Install `crewai[tools]`. You can pass the Vinkius URL directly into your agent's definition using `mcps=["YOUR_VINKIUS_URL"]`. The framework handles the HTTP transport automatically.

Yes. For advanced setups, import `MCPServerHTTP` from `crewai.mcp`. You can apply a `tool_filter` so your Analyst Agent only accesses `list_financial_events` while your Inventory Agent only sees `list_fba_inventory`.

Your agents can operate sequentially. One agent triggers `create_report`, and a separate Monitor Agent runs in a loop checking `get_report_status` until the file is ready for analysis.

CrewAI supports stdio, SSE, and Streamable HTTP. Vinkius provides a single endpoint token, so your agents connect over secure HTTP without managing complex local environment variables.

We secure the transport layer, not your local memory. When your agents pull product types or ASINs, the Vinkius infrastructure processes the request inside a single-use V8 sandbox. Once the data hits your local CrewAI environment, the sandbox dies.

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