How to Use the Nimbata MCP in OpenAI Agents SDK

Q: How do I configure Nimbata with OpenAI Agents SDK?

Install openai-agents and initialize MCPServerStreamableHttp pointing to your Vinkius gateway. Pass this server instance inside the mcpservers list when instantiating your Agent, and set cacheToolsList=True to speed up tool discovery.

Q: How do I search for specific caller records?

Your agent invokes searchcalls with specific parameters like date ranges or status. This returns a structured list of call metadata, which the agent can filter further before requesting deep-dive metrics via getcalldetails.

Track and route phone call conversions dynamically inside your OpenAI Agents SDK workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nimbata MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Call Source Setup in OpenAI Agents SDK

Your agent uses the `create_source` tool to dynamically generate new marketing sources when you launch ad variants in your OpenAI Agents SDK pipeline. This setup bypasses manual dashboard configuration entirely. Once configured, the agent runs `list_sources` to map active tracking pools back to your OpenAI tracing dashboard using the Nimbata MCP Server. Verification happens automatically before the agent proceeds to downstream tasks.

Analyze Customer Audio Safely

Your agent calls `get_call_recording` to pull raw MP3 streams directly into your OpenAI Agents SDK processing pipeline for transcription. OpenAI Agents SDK enforces runtime guardrails, preventing the model from extracting audio from restricted caller regions. To verify call state before pulling heavy files, the agent queries `get_call_details` or `list_calls` first. This multi-step check ensures you only run expensive transcription pipelines on answered calls longer than thirty seconds.

Generate Direct Attribution Reports

This integration uses `get_source_report` to feed conversion metrics directly into your agent-to-agent handoffs within the OpenAI Agents SDK. A specialized analytics agent can inspect the source report and hand off high-value call sources to your budget-optimization agent. The agent runs `get_call_report` to parse call duration and caller location trends without manual data exports. This setup relies on `check_nimbata_status` during initialization to confirm your API credentials are live before initiating high-volume analytical sweeps across the MCP Server.

Setup guide

Set up Nimbata 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 Nimbata tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` and initialize `MCPServerStreamableHttp` pointing to your Vinkius gateway. Pass this server instance inside the `mcp_servers` list when instantiating your Agent, and set `cacheToolsList=True` to speed up tool discovery.

No, but the agent can query existing inventory. Your agent uses `list_numbers` to fetch active tracking numbers and `get_number` to inspect specific routing destinations, allowing it to allocate existing numbers to newly created sources.

The agent relies on standard Python exception handling and OpenAI's built-in tracing. Before running complex search operations with `search_calls`, the agent runs `check_nimbata_status` to verify that the connection to the external gateway is active.

Your agent invokes `search_calls` with specific parameters like date ranges or status. This returns a structured list of call metadata, which the agent can filter further before requesting deep-dive metrics via `get_call_details`.

Yes, because raw caller numbers and audio files retrieved via `get_call_recording` remain within your isolated V8 sandbox on Vinkius. The OpenAI Agents SDK processes this sensitive customer information locally inside your secure Python environment, never exposing raw recordings to external training datasets.

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