How to Use the Gong MCP in OpenAI Agents SDK

Q: How do I register the Gong MCP Server inside my OpenAI Agents SDK project?

Use MCPServerStreamableHttp to point to your Vinkius endpoint. Pass the server instance directly into the mcpservers list when initializing your Agent object.

Q: Can an OpenAI Agents SDK agent handle multiple Gong transcripts without hitting rate limits?

Yes, by configuring cacheToolsList=True during initialization to reduce schema discovery overhead. The agent can then sequentially call gettranscript for multiple records while managing token usage through standard OpenAI system controls.

Q: What happens if the connection to the API drops during an active run?

Your agent will receive an error when invoking tools like checkgongstatus or getcall. You should implement standard Python retry logic around your agent's execution loop to handle temporary network drops gracefully.

Run production OpenAI Agents SDK pipelines that analyze Gong call data, audit performance, and track deals with strict guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gong MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safeguard Gong Data in OpenAI Agents SDK

When your OpenAI Agents SDK agent runs, it needs strict boundaries before calling tools like `get_transcript` or `list_deals`. This integration hooks directly into OpenAI's native guardrails, allowing you to intercept and validate requests before the agent exposes sensitive sales call details. If an agent attempts to call `get_user_stats` on an unauthorized team member, the SDK blocks the action instantly. You get clean, safe execution with full tracing visible right inside your OpenAI dashboard.

Handoff Call Analysis to Specialized Agents

Let one agent fetch raw data using `list_calls_by_date` and pass the context to a specialized coaching agent. The second agent can then query `list_scorecards` to evaluate the rep's performance against historical benchmarks. This multi-agent handoff pattern prevents a single agent from getting bogged down in massive datasets. By splitting the work, your OpenAI setup processes transcripts faster and returns sharper, more targeted coaching insights.

Auto-Discover Gong Tools Instantly

Skip the manual tool definition boilerplate entirely when configuring your server. This MCP Server allows your OpenAI agents to automatically discover and map all 14 Gong endpoints, including `get_call_stats` and `list_library_calls`, with zero configuration. Simply register the streamable HTTP server and let the SDK handle the schema translation. Setting `cacheToolsList=True` ensures your production agents load these tools instantly without hitting API rate limits during startup.

Setup guide

Set up Gong 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 Gong tools at runtime.
3

Create your Agent

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

Run the agent

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

Use `MCPServerStreamableHttp` to point to your Vinkius endpoint. Pass the server instance directly into the `mcp_servers` list when initializing your `Agent` object.

Yes, by configuring `cacheToolsList=True` during initialization to reduce schema discovery overhead. The agent can then sequentially call `get_transcript` for multiple records while managing token usage through standard OpenAI system controls.

You define specialized agents for different tasks. Keep your deal-tracking agent separate by only passing the MCP Server instance to that specific constructor, preventing your coaching agents from ever calling `list_deals`.

Your agent will receive an error when invoking tools like `check_gong_status` or `get_call`. You should implement standard Python retry logic around your agent's execution loop to handle temporary network drops gracefully.

All transcript and scorecard data processed by the MCP Server runs inside isolated V8 sandboxes that tear down immediately after execution. Your API credentials never persist on disk, and no raw conversational data is stored or logged.

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