How to Use the Gong MCP in AutoGen

Q: How do AutoGen agents share access to the Gong MCP Server?

You register the tools with your AssistantAgent using the mcpservertools helper. Once registered, any agent in your AutoGen group chat can invoke tools like gettranscript or listcalls during their conversation.

Q: Can I limit which AutoGen agent can call specific Gong tools?

Yes. You can assign specific tools, like getcallmedia, to a dedicated auditor agent while restricting other agents to only calling analytical tools like getinteractionstats.

Q: How does AutoGen handle complex filtering when searching Gong calls?

The searchcalls tool supports complex filters. Your AutoGen planner agent can construct the exact JSON filter payload and pass it to the executor agent to retrieve precise call lists.

Q: Is our Gong API key exposed to the agents?

No. Your Gong API key and call metadata retrieved via getcall are securely isolated in your Vinkius dashboard. The AutoGen agents only receive the raw text outputs over encrypted channels, keeping your access credentials completely hidden.

Run AutoGen agents to debate sales performance and audit Gong transcripts for compliance.

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 AutoGen

Create your Vinkius account to connect Gong to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-agent Gong audits in AutoGen

Set up a debate between a compliance agent and a sales coach in AutoGen using this MCP Server. The AutoGen compliance agent pulls Gong transcripts via `get_transcript` to scan for legal disclaimers, while the coaching agent reviews `list_scorecards` to evaluate the rep's soft skills. They discuss their findings in a shared AutoGen chat channel, pointing out specific Gong timestamps retrieved from `get_call_media`. You get a balanced, thoroughly debated evaluation of the Gong call instead of a single biased opinion from one agent.

Track tracker hits with agent consensus

Let your AutoGen agents collaborate on competitive intelligence over MCP. One AutoGen agent uses `list_trackers` to pull active competitor keywords, while another runs `search_calls` to find where those keywords popped up in recent Gong sales conversations. A third AutoGen manager agent synthesizes the findings to determine if a competitor is gaining traction in a specific territory based on Gong data. This multi-agent setup ensures your AutoGen pipeline does not miss critical market shifts in Gong.

Analyze team stats via AutoGen debate

Optimize your sales team's calendar efficiency using AutoGen agent conversations. An AutoGen performance agent analyzes team metrics using `get_interaction_stats` and argues for shorter discovery calls, while a customer success agent checks `list_accounts` to see if shorter Gong calls harm retention. The AutoGen agents negotiate a middle ground based on actual Gong data. This collaborative analysis prevents you from making rash operational changes to your Gong sales workflow.

Setup guide

Set up Gong MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Gong tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Gong_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Gong data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Gong_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Gong data")
    print(result.messages[-1].content)

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 AutoGen

You register the tools with your `AssistantAgent` using the `mcp_server_tools` helper. Once registered, any agent in your AutoGen group chat can invoke tools like `get_transcript` or `list_calls` during their conversation.

Yes. You can assign specific tools, like `get_call_media`, to a dedicated auditor agent while restricting other agents to only calling analytical tools like `get_interaction_stats`.

The `search_calls` tool supports complex filters. Your AutoGen planner agent can construct the exact JSON filter payload and pass it to the executor agent to retrieve precise call lists.

AutoGen connects to the Vinkius hosted server using the Streamable HTTP transport. The `McpToolAdapter` automatically translates the Gong tool schemas into the format AutoGen expects.

No. Your Gong API key and call metadata retrieved via `get_call` are securely isolated in your Vinkius dashboard. The AutoGen agents only receive the raw text outputs over encrypted channels, keeping your access credentials completely hidden.

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