How to Use the OneLocal LocalReviews MCP in OpenAI Agents SDK

Q: How do I connect the OneLocal LocalReviews MCP Server to OpenAI Agents SDK?

Use the MCPServerStreamableHttp class. Pass your Vinkius endpoint URL into the params, wrap it in an async context manager, and hand it to the Agent constructor. The SDK auto-discovers all ten tools instantly.

Q: Can the agent verify the OneLocal API connection?

Yes, the agent can call checkonelocalstatus to confirm the API is responding. If the connection fails, your OpenAI guardrails can pause the workflow before it attempts to pull data.

Q: Does OneLocal LocalReviews work with OpenAI Agents SDK tool caching?

It does. Set cacheToolsList=True when initializing the server. This prevents the agent from re-fetching the tool schemas for things like getreview on every single turn.

Q: How do OneLocal LocalReviews and OpenAI Agents SDK handle customer phone numbers and emails?

The requestreview tool processes direct contact info like phone numbers and email addresses. The Vinkius V8 Isolate Sandbox executes this request in an ephemeral environment. It destroys the memory state the millisecond the OneLocal API confirms delivery.

Build production-ready marketing agents with OpenAI Agents SDK to track local business reputation and trigger review requests safely.

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 OpenAI Agents SDK

Create your Vinkius account to connect OneLocal LocalReviews to OpenAI Agents SDK — 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automate reputation loops via MCP Server

Your OpenAI agent needs real social proof data to make decisions. By connecting this MCP Server, the agent can hit `get_reputation` to read aggregate scores across platforms. If a location's rating drops below your threshold, the system catches it immediately. You then set up a specialized outreach agent. It pulls the latest feedback using `list_reviews` and flags negative sentiment. Because of the SDK's built-in guardrails, you can require human approval before the agent drafts any public responses.

Trigger review requests safely

Getting more reviews means asking for them. The agent can call `request_review` to send SMS or email invites directly to recent customers. Passing the customer details is simple, and the tool handles the delivery through the OneLocal API. Tracing this in the OpenAI dashboard shows exactly when and why an invite went out. Marketers can map these actions back to specific campaigns by running `list_campaigns` and `get_campaign`, giving them a clear audit trail of automated outreach.

Map local business footprints

Multi-location businesses create routing headaches for agents. The `list_locations` tool pulls every storefront your account manages. Routing logic uses this to isolate data so the system doesn't accidentally send a review link for the wrong branch. Once it identifies the correct branch with `get_location`, it checks the referral pipeline using `list_referrals`. Developers get a complete picture of customer acquisition through this MCP integration without writing custom API wrappers or handling authentication logic.

Setup guide

Set up OneLocal LocalReviews MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all OneLocal LocalReviews tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives OneLocal LocalReviews tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate OneLocal LocalReviews tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="OneLocal LocalReviews Agent",
            instructions="You have access to OneLocal LocalReviews tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Use the `MCPServerStreamableHttp` class. Pass your Vinkius endpoint URL into the params, wrap it in an async context manager, and hand it to the Agent constructor. The SDK auto-discovers all ten tools instantly.

Yes, the agent can call `check_onelocal_status` to confirm the API is responding. If the connection fails, your OpenAI guardrails can pause the workflow before it attempts to pull data.

It does. Set `cacheToolsList=True` when initializing the server. This prevents the agent from re-fetching the tool schemas for things like `get_review` on every single turn.

You enforce this at the agent prompt level or by wrapping the tool. The MCP standard exposes the raw `list_locations` output, so your OpenAI routing agent needs instructions to filter the results before passing them down the chain.

The `request_review` tool processes direct contact info like phone numbers and email addresses. The Vinkius V8 Isolate Sandbox executes this request in an ephemeral environment. It destroys the memory state the millisecond the OneLocal API confirms delivery.

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