How do I obtain the Access Token required for authentication?

You must complete the OAuth 2.0 authorization flow using your App Key through your specific seller account on the Temu Open Platform. The flow will generate an Access Token that grants scoped permissions to your store's order, inventory, and logistics data.

Can I manage inventory across multiple SKU variants simultaneously?

Yes! The `sync_inventory` tool accepts batch SKU updates. You can push quantity changes for multiple product variants in a single call, and the engine handles all MD5 signature computation and parameter encoding automatically.

Is there any risk of accidentally modifying live product listings or canceling orders?

All write operations require explicit parameters — order IDs, SKU identifiers, tracking numbers — that must be deliberately specified. The Access Token is scoped to your seller account, and the MD5 signature layer prevents request forgery. Critical actions like order cancellation are logged and require confirmation parameters.

Temu Seller Hub MCP Server for Google ADK 12 tools — connect in under 2 minutes

Name: Temu Seller Hub
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 12 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Temu Seller Hub as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

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

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="temu_seller_hub_agent",
    instruction=(
        "You help users interact with Temu Seller Hub "
        "using 12 available tools."
    ),
    tools=[mcp_tools],
)

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 Temu Seller Hub MCP Server

Bridge your AI agents directly into the Temu Open Platform, Pinduoduo's global cross-border marketplace processing millions of orders daily. Automate the complete supply-chain lifecycle without navigating complex seller consoles.

Google ADK natively supports Temu Seller Hub as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 12 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Order Management — List incoming orders from global buyers, retrieve full line-item details, and monitor payment status dynamically
Fulfillment & Logistics — Query valid shipping carriers, mark orders as shipped with tracking numbers, and monitor delivery milestones
Inventory Sync — Automate stock quantity updates across SKUs preventing overselling and stockout situations
Product Catalog — Pull published product listings and detailed goods specifications for auditing and optimization
Returns Handling — Track incoming RMA requests, query refund states, and manage reverse logistics efficiently

The Temu Seller Hub MCP Server exposes 12 tools through the Vinkius. Connect it to Google ADK 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 Temu Seller Hub to Google ADK via MCP

Follow these steps to integrate the Temu Seller Hub MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 12 tools from Temu Seller Hub via MCP

Why Use Google ADK with the Temu Seller Hub MCP Server

Google ADK provides unique advantages when paired with Temu Seller Hub through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Temu Seller Hub

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine Temu Seller Hub tools with BigQuery, Vertex AI, and Cloud Functions

Temu Seller Hub + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Temu Seller Hub MCP Server delivers measurable value.

Enterprise data agents: ADK agents query Temu Seller Hub and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine Temu Seller Hub tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query Temu Seller Hub regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Temu Seller Hub

Temu Seller Hub MCP Tools for Google ADK (12)

These 12 tools become available when you connect Temu Seller Hub to Google ADK via MCP:

create_ship_order

Uses the v2 ship order creation API. Create a shipping order to fulfill a delivery

get_aftersale_list

List after-sale / return requests

get_goods_detail

Get full product details for a specific item

get_goods_list

List published products on Temu store

get_goods_sku

Get SKU-level details for a product

get_inventory

List inventory levels across all SKUs

get_logistics_companies

Get supported shipping carriers on Temu

get_order_detail

Get full details for a specific Temu order

get_order_list

Supports pagination and optional status filter. Uses create_after/create_before timestamps. Get a list of Temu orders by creation date range

get_purchase_orders

Used to track incoming stock requests from the platform. Get restocking / purchase orders from Temu

get_ship_order_list

List existing shipping orders

sync_inventory

Update inventory stock quantity for a specific SKU

Example Prompts for Temu Seller Hub in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with Temu Seller Hub immediately.

"Get my Temu orders from the last 24 hours and summarize pending fulfillment."

"Mark order TMU-2024-88712 as shipped with tracking number YT2048391004."

"Update inventory for SKU TMU-SHOE-42BLK to 250 units."

Troubleshooting Temu Seller Hub MCP Server with Google ADK

Common issues when connecting Temu Seller Hub to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

Temu Seller Hub + Google ADK FAQ

Common questions about integrating Temu Seller Hub MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.