How to Use the Nango (Unified API & Integration Platform) MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK handle failed connections with Nango (Unified API & Integration Platform)?

If your agent calls getconnection for a non-existent ID, it gets a clear error. The SDK's built-in tracing shows the failed tool call, so you can debug why the agent tried to access a bad connection. This prevents silent failures.

Give your OpenAI Agent a full view of your SaaS integrations. Let it audit connections, check syncs, and manage your Nango unified API directly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nango (Unified API & Integration Platform) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Nango (Unified API & Integration Platform) 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 Nango (Unified API & Integration Platform) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Every Connection

Your agent can now act as your integration watchdog. Use `list_connections` to get a full inventory of every active OAuth session managed by Nango. No more guessing which tokens are live. When an issue pops up, the agent can drill down with `get_connection`. It gets the specific metadata for that connection—provider, creation date, and status—so it can flag expired tokens or failed auths before your users do.

Track Data Syncs in Real Time

Stop flying blind on data synchronization. With this MCP Server, your OpenAI Agent can query `list_syncs` to see the complete history for any connection. You get a log of successes, failures, and timings. If a sync fails, the agent can immediately use `list_records` to check the last good data pull. This gives it the context to retry the sync, notify an on-call engineer, or halt dependent workflows, all within the safety guardrails of the OpenAI SDK.

Manage Integrations, Not Just Data

Your agent's awareness isn't just limited to data. It can call `list_integrations` to see every integration template you've configured in Nango. This is great for reporting or building dynamic workflows with your agent. It can also use `get_integration` to fetch the specific parameters for one integration, or `get_environment` to understand the runtime context. It's how you build agents that can self-diagnose configuration issues across your entire stack with this MCP toolset.

Setup guide

Set up Nango (Unified API & Integration Platform) 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 Nango (Unified API & Integration Platform) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Nango (Unified API & Integration Platform) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Nango (Unified API & Integration Platform) 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="Nango (Unified API & Integration Platform) Agent",
            instructions="You have access to Nango (Unified API & Integration Platform) 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 Nango. 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 Nango (Unified API & Integration Platform) 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 Nango (Unified API & Integration Platform) MCP in OpenAI Agents SDK

The MCP server gives your agent direct, secure access to your entire integration layer. It can independently audit connections and check data syncs without you writing custom API calls. It's about giving the agent the tools to manage the system itself.

No. The OpenAI Agents SDK discovers all the Nango tools automatically from the MCP server endpoint. Just pass the server to the agent constructor and it's ready to go.

If your agent calls `get_connection` for a non-existent ID, it gets a clear error. The SDK's built-in tracing shows the failed tool call, so you can debug why the agent tried to access a bad connection. This prevents silent failures.

Yes, you can control this on the agent itself. While the MCP server exposes all tools, you can configure the agent's permissions to restrict it to read-only operations like `list_syncs`, preventing it from performing actions you haven't approved.

The server queries Nango for integration metadata, connection details, and sync statuses. It can also access the actual synced record data via `list_records`. Vinkius handles the auth token securely and all operations run in an ephemeral, zero-trust sandbox for each request.

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