How to Use the CustomerGauge MCP in OpenAI Agents SDK

Build production-ready B2B experience agents with the OpenAI Agents SDK by connecting an MCP Server directly to CustomerGauge data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CustomerGauge MCP to OpenAI Agents SDK

Create your Vinkius account to connect CustomerGauge to OpenAI Agents SDK 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 CustomerGauge with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect CustomerGauge to the OpenAI Agents SDK

Your deployed agent executes `get_account_nps` and `get_portfolio_nps_summary` to pull executive reporting metrics straight into your operational workflows. The OpenAI Agents SDK auto-discovers these MCP tools the moment you pass the Vinkius endpoint to the agent constructor. Handoffs between specialized agents happen naturally when dealing with complex accounts. A triage agent can run `list_b2b_accounts` to identify at-risk clients, then pass the context to a retention agent that pulls exact verbatim comments using `get_response_details`.

Build safe revenue impact workflows

Calling `list_revenue_impact_data` resolves monetary values tied to customer satisfaction scores directly from your CustomerGauge environment. Built-in guardrails validate these financial metrics before your agent takes action on high-value accounts. Tracing through the OpenAI dashboard shows exactly how your agent navigates the business unit hierarchy via `get_business_unit_nps`. You see every API request and response, ensuring the agent sticks to permitted data boundaries.

Analyze feedback at scale

The `search_responses_by_keyword` tool resolves feedback entries matching specific terms across your entire survey repository. Your agent reads actual customer sentiment instead of guessing what accounts care about. Digging deeper requires context. When a keyword flags a negative trend, the agent triggers `get_contact_profile` to pull the interaction history for that specific individual.

Setup guide

Set up CustomerGauge 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 CustomerGauge tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate CustomerGauge 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="CustomerGauge Agent",
            instructions="You have access to CustomerGauge 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 CustomerGauge. 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 CustomerGauge 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 CustomerGauge MCP in OpenAI Agents SDK

Install the openai-agents package and initialize MCPServerStreamableHttp with your Vinkius URL. Pass it to your agent constructor via the mcp_servers parameter to expose the tools.

Yes. You set cacheToolsList=True during initialization. This prevents the agent from re-fetching the tool definitions on every turn.

The server exposes tools for different granularity levels. Your agent can read account-specific metrics, business unit rollups, or global portfolio summaries.

The OpenAI dashboard automatically logs every MCP tool execution. You see exactly when the agent requests survey responses and what data returns.

Vinkius isolates the environment in a V8 sandbox with ephemeral execution. Your agent only reads verbatim comments and respondent metadata during active sessions, leaving no persistent footprint.

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