How to Use the Junip MCP in Google ADK

Q: How do I pass Junip tools into Google ADK?

Install the google-adk package. Initialize McpToolset with StreamableHttpServerParameters pointing to your URL. Inject that toolset directly into the tools list of your LlmAgent.

Q: Can Google ADK filter which Junip tools the agent sees?

Yes. Use the toolnames argument when setting up the toolset. You can restrict the agent to just listthemes or listanswers if you want a strictly read-only audit bot.

Connect the Junip MCP Server to Google ADK and let Gemini agents analyze millions of reviews.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Junip MCP to Google ADK

Create your Vinkius account to connect Junip to Google ADK 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 Junip with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Cross-reference Junip data with Google ADK

`list_reviews` returns ratings, review content, and reviewer names to your Gemini agent. You can dump this raw feedback straight into BigQuery for long-term storage. Gemini's massive context window means the agent holds thousands of these reviews in memory at once without losing track of the details. Fetching individual context is just as simple. `get_review` pulls the specific metadata, custom question responses, and photo links. The agent reads the image URLs, passes them to Vertex AI for vision analysis, and tags the review based on the visual content.

Query product catalogs

`list_products` includes product names, IDs, and aggregate review metrics to identify which items have feedback. You initialize the `McpToolset` with your HTTP transport and pass it to the `LlmAgent`. The agent cross-checks these IDs against your Google Cloud inventory databases. When an anomaly appears in the aggregate data, the agent investigates. It fires `get_product` to read the detailed performance summary of that exact SKU. If you want to restrict access, you can filter the exposed tools so the agent only sees read-only endpoints.

Manage Q&A and MCP Server campaigns

`list_campaigns` exposes your active efforts to collect new customer reviews. The agent monitors these active review requests and correlates them with traffic spikes in Google Analytics. It knows exactly which campaigns are driving the most user interaction. Customer inquiries need fast routing. `list_questions` returns question text, status, and associated products. The agent checks `get_account` to verify access levels, pulls the pending questions, and routes them to the correct department via your existing Google Workspace integrations.

Setup guide

Set up Junip 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 Junip 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="Junip_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Junip 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 Junip. 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 Junip 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 Junip MCP in Google ADK

Install the `google-adk` package. Initialize `McpToolset` with `StreamableHttpServerParameters` pointing to your URL. Inject that toolset directly into the `tools` list of your `LlmAgent`.

Yes. Use the `tool_names` argument when setting up the toolset. You can restrict the agent to just `list_themes` or `list_answers` if you want a strictly read-only audit bot.

Gemini's massive token context window easily swallows huge API payloads. You can pull hundreds of pages using `list_reviews` and the agent will process the entire batch.

You can do this directly. The agent extracts the JSON from endpoints like `list_products` and formats it for immediate insertion into your BigQuery tables.

The MCP integration touches custom question responses, reviewer names, and active campaign metrics. You control the deployment environment. Google ADK executes the tool calls within your VPC, keeping the raw e-commerce data inside your established perimeter.

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