How do I get my Amazon SP-API credentials?

You need to register a private application in the Amazon Seller Central (Partner Network > Develop Apps). You will get an LwA Client ID and Secret. You then self-authorize the app to get a long-lived Refresh Token.

Which region should I choose?

Select the region that matches your target marketplace: **NA** (North America - US, CA, MX, BR), **EU** (Europe - UK, DE, FR, IT, ES, etc.), or **FE** (Far East - JP, AU, SG).

Can I request PII data like customer names?

This MCP server uses standard SP-API tokens. Some PII data (Personally Identifiable Information) in orders requires a Restricted Data Token (RDT), which must be specifically requested in the API call and authorized in your app's roles.

Amazon Selling Partner MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Amazon Selling Partner
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Amazon Selling Partner through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Amazon Selling Partner "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Amazon Selling Partner?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Amazon Selling Partner MCP Server

Connect your Amazon Selling Partner (SP-API) account to your AI agent to unlock professional e-commerce and marketplace orchestration. From managing incoming orders and auditing FBA inventory to researching the Amazon product catalog and requesting asynchronous reports, your agent handles your seller operations through natural conversation.

Pydantic AI validates every Amazon Selling Partner tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Order Management — List incoming orders and retrieve detailed item lists for fulfillment
FBA Inventory Auditing — Retrieve inventory summaries and monitor stock levels across Amazon fulfillment centers
Catalog Research — Search the Amazon catalog by ASIN or keywords to retrieve technical product metadata
Reporting Orchestration — Request asynchronous seller reports and monitor their processing statuses
Financial Insights — Retrieve financial event groups and marketplace participation details directly from chat

The Amazon Selling Partner MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Amazon Selling Partner to Pydantic AI via MCP

Follow these steps to integrate the Amazon Selling Partner MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Amazon Selling Partner with type-safe schemas

Why Use Pydantic AI with the Amazon Selling Partner MCP Server

Pydantic AI provides unique advantages when paired with Amazon Selling Partner through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Amazon Selling Partner integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Amazon Selling Partner connection logic from agent behavior for testable, maintainable code

Amazon Selling Partner + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Amazon Selling Partner MCP Server delivers measurable value.

Type-safe data pipelines: query Amazon Selling Partner with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Amazon Selling Partner tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Amazon Selling Partner and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Amazon Selling Partner responses and write comprehensive agent tests

Amazon Selling Partner MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Amazon Selling Partner to Pydantic AI via MCP:

create_report

g. GET_MERCHANT_LISTINGS_ALL_DATA). Request a report

get_catalog_item

Get catalog item

get_order_items

Get order items

get_report_status

Check report status

list_fba_inventory

List FBA inventory

list_financial_events

List financial events

list_marketplaces

List marketplaces

list_orders

List Amazon orders

list_product_types

List product types

search_catalog

Search Amazon catalog

Example Prompts for Amazon Selling Partner in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Amazon Selling Partner immediately.

"List my recent Amazon orders."

"Show the FBA inventory summary for my top products."

"Search the Amazon catalog for ASIN 'B012345678'."

Troubleshooting Amazon Selling Partner MCP Server with Pydantic AI

Common issues when connecting Amazon Selling Partner to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Amazon Selling Partner + Pydantic AI FAQ

Common questions about integrating Amazon Selling Partner MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Amazon Selling Partner MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.