How to Use the Froged MCP in OpenAI Agents SDK

Q: Does the Froged MCP Server support agent handoffs?

The server provides raw tools like sendchatmessage. You configure the handoff logic inside your OpenAI Agents SDK setup to route complex chats to specialized agents.

Q: How do I verify the Froged connection is working?

Call the verifyapistatus tool. It returns a simple boolean response so your agent knows the API is reachable before attempting to pull a massive list of contacts.

Build production customer support agents that manage Froged contacts and chats directly through the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Froged MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Support with OpenAI Agents SDK

Your agent uses `list_support_conversations` and `get_chat_details` to read inbound tickets directly from Froged. You do not need to build custom pollers or webhooks. The OpenAI Agents SDK auto-discovers these tools and maps them to your specialized support agent. When a customer asks a known question, the agent searches `list_kb_articles` for the exact documentation. It then drafts a reply and fires `send_chat_message` to resolve the issue. If the request triggers a safety guardrail, the SDK hands the context off to a human escalation agent instead.

Track User Behavior in Production

This MCP Server exposes `track_custom_event` so your agents can log user actions during a conversation. If an agent successfully downgrades a billing plan, it immediately pushes that event into Froged. You get a clean audit trail right in your dashboard. Agents can also read historical data using `list_behavioral_events`. This means your agent knows exactly which features a user tried before opening a ticket. You stop asking customers for steps to reproduce because the agent already pulled their timeline.

Read and Update Contact Metadata

The `upsert_contact` tool lets your agent update user profiles on the fly. If a user mentions a new phone number or company size in chat, the agent updates their Froged record instantly. Before answering pricing questions, the agent runs `get_contact_details` to check the user's current tier. You can enforce guardrails that prevent the agent from promising enterprise features to basic-tier users. Everything gets traced back through the OpenAI dashboard for your review.

Setup guide

Set up Froged 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 Froged tools at runtime.
3

Create your Agent

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

Run the agent

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

Install openai-agents via pip. Create an MCPServerStreamableHttp instance with your Froged endpoint URL. Pass it to your Agent constructor in the mcp_servers list.

Yes. Set cacheToolsList=True when initializing the server connection. This prevents the SDK from re-fetching the schema for tools like list_marketing_campaigns on every single request.

The server provides raw tools like send_chat_message. You configure the handoff logic inside your OpenAI Agents SDK setup to route complex chats to specialized agents.

Call the verify_api_status tool. It returns a simple boolean response so your agent knows the API is reachable before attempting to pull a massive list of contacts.

The MCP integration processes raw chat transcripts and user metadata. Vinkius runs this connection inside an ephemeral V8 Isolate Sandbox. Your endpoint token is the only authentication used, and no conversation data is stored on our infrastructure after the request completes.

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