How to Use the Searchspring MCP in Google ADK

Q: How do I restrict which Searchspring MCP tools are exposed to my Google ADK agent?

You can use the optional toolnames filter when initializing the Google ADK McpToolset. This lets you limit your Google ADK agent to only use Searchspring's searchsku or suggestqueries if you want to keep its scope narrow.

Feed Searchspring catalog data directly into your Google ADK pipelines to power Gemini-driven enterprise search via MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Searchspring MCP to Google ADK

Create your Vinkius account to connect Searchspring to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Searchspring with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Long-Context Catalog Reasoning

Gemini models love massive context windows, but they need accurate inputs from your Searchspring catalog. By linking this MCP Server to your Google ADK setup, your agent can pull massive product lists using `search_products` and analyze them all at once. The Google ADK agent can execute `search_brand` to gather hundreds of Searchspring items, then use Gemini's long-context window to spot trends or build complex product recommendations. You do not have to worry about running out of token space when dumping raw Searchspring catalog payloads into the Google ADK context.

Merging Searchspring MCP Server Data with BigQuery

Enterprise commerce relies on historical data. Your Google ADK agent can query your internal warehouse in BigQuery, identify low-performing items, and then call `search_sku` to check their current Searchspring catalog status. By combining BigQuery and Searchspring sources, the Google ADK agent can automatically adjust search parameters using `search_custom`. This bridges the gap between your offline Google Cloud analytics and live Searchspring search configurations without manual developer intervention.

Deep Category Tree Navigation

Complex Searchspring retail catalogs have deeply nested structures that trip up basic Google ADK agents. This toolset lets your Google ADK agent call `search_category` to map out the exact hierarchy of your store. Once the Google ADK agent understands the Searchspring category path, it can apply precise filters via `search_filtered` or adjust pagination using `search_pagination`. This ensures Gemini navigates your Searchspring e-commerce store with the same logic your human merchandisers use.

Setup guide

Set up Searchspring MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Searchspring tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Searchspring_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Searchspring tools via MCP.",
    tools=mcp_tools,
)

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 Searchspring. 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 Searchspring 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 Searchspring MCP in Google ADK

Yes, you can run a Google ADK pipeline that pulls offline sales trends from BigQuery and feeds them into Searchspring's `search_products` tool to find matching inventory. The Google ADK coordinates both tools in a single unified execution loop.

You can use the optional tool_names filter when initializing the Google ADK `McpToolset`. This lets you limit your Google ADK agent to only use Searchspring's `search_sku` or `suggest_queries` if you want to keep its scope narrow.

Yes, the Google ADK supports both Stdio and HTTP transport layers for Searchspring. For most cloud deployments on Vertex AI, you will connect to the hosted Searchspring endpoint via the streamable HTTP transport.

Gemini easily ingests the large JSON payloads returned by custom Searchspring queries. The Google ADK passes the raw output from tools like `search_pagination` directly into the model's context window without truncation.

The MCP server only accesses catalog metadata, pricing, inventory levels, and SKU details within the Google ADK pipeline. No customer PII is ever touched. All API communication runs through an isolated V8 sandbox with end-to-end encryption, ensuring your proprietary catalog data remains secure.

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