How to Use the OneLocal LocalReviews MCP in Google ADK

Q: How do I initialize the OneLocal LocalReviews MCP Server in Google ADK?

Install google-adk and create a McpToolset. Pass your Vinkius server URL into StreamableHttpServerParameters, then hand that toolset to your LlmAgent.

Q: Can I restrict which OneLocal tools the Gemini agent sees?

Yes, you can use the toolnames filter when setting up the toolset. This lets you expose listreviews for analysis while blocking requestreview to prevent accidental customer outreach.

Q: How do OneLocal LocalReviews and Google ADK handle referral tracking?

The agent calls listreferrals to pull the active referral data from OneLocal. Gemini can then parse this list and match the referring customers against your Google Cloud CRM records.

Q: What happens to the review text processed by OneLocal LocalReviews and Google ADK?

Tools like getreview pull raw customer feedback, including names and complaints. Vinkius routes this data through a zero-trust architecture. No request payloads are ever logged or stored on our infrastructure before hitting your Gemini agent.

Connect OneLocal LocalReviews to Google ADK and let Gemini agents analyze local feedback against your BigQuery customer data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect OneLocal LocalReviews MCP to Google ADK

Create your Vinkius account to connect OneLocal LocalReviews 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 OneLocal LocalReviews with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Cross-reference reviews with BigQuery

Gemini's massive context window changes how we handle customer feedback. The MCP integration lets the agent dump thousands of records from `list_reviews` straight into memory. It reads the raw text, identifies complaints, and matches them to internal sales data. Nobody wants to build a custom ETL pipeline for this. Your Google ADK agent pulls specific feedback using `get_review`, structures the sentiment, and pushes those insights directly into BigQuery for the marketing team to query.

Trigger campaigns from Google ADK

Reading data is only half the job. When the Gemini agent spots a happy customer in your Vertex AI pipeline, it fires off `request_review`. The tool sends the OneLocal invite via text or email without writing a single HTTP request. Tracking the success of these automated asks happens through this MCP Server. The agent runs `list_campaigns` to see which outreach efforts actually convert. If a specific location lags behind, `get_campaign` shows exactly where the drop-off happens.

Monitor multi-location reputation

Franchise operators need aggregate metrics. The `get_reputation` tool hands your agent the high-level scores across Google, Yelp, and Facebook. If the numbers dip, the agent knows immediately. It then isolates the problem. By calling `list_locations` and `get_location`, the agent figures out which storefront is dragging the average down. It checks `check_onelocal_status` first to ensure the API is live, then builds a targeted report for that specific manager.

Setup guide

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

Install `google-adk` and create a `McpToolset`. Pass your Vinkius server URL into `StreamableHttpServerParameters`, then hand that toolset to your `LlmAgent`.

Yes, you can use the `tool_names` filter when setting up the toolset. This lets you expose `list_reviews` for analysis while blocking `request_review` to prevent accidental customer outreach.

The agent calls `list_referrals` to pull the active referral data from OneLocal. Gemini can then parse this list and match the referring customers against your Google Cloud CRM records.

It works perfectly. Since the MCP standard uses HTTP transport, your Cloud Run agent just makes outbound requests to the Vinkius endpoint. There are no local binaries to manage.

Tools like `get_review` pull raw customer feedback, including names and complaints. Vinkius routes this data through a zero-trust architecture. No request payloads are ever logged or stored on our infrastructure before hitting your Gemini agent.

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