How to Use the Gong MCP in Google ADK

Q: Can I restrict which Gong tools are visible to my Google ADK agent?

Yes. You can use the optional toolnames filter in the McpToolset configuration to restrict access. For example, you can expose only listcalls and gettranscript while hiding administrative MCP tools.

Q: How does Google ADK handle large payloads from Gong call media?

When your agent invokes getcallmedia, the tool returns metadata and URLs for the recording. Google ADK processes this structured response, allowing your agent to reference the media files without hitting payload bottlenecks.

Q: Can my MCP agent query CRM accounts linked in my sales records?

Yes. The listaccounts tool allows your agent to retrieve linked CRM accounts. The agent can then use getaccount to pull specific details for any account flagged during transcript analysis.

Q: How does this setup protect my Gong user profiles and CRM account details?

Your CRM account lists and user metadata fetched via getuser are processed strictly within your Google Cloud boundary. Vinkius handles the authentication token securely, ensuring no credentials or account profiles are exposed to external networks.

Feed Gong conversation data directly to Google ADK agents to run deep analysis across millions of tokens.

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 Google ADK

Create your Vinkius account to connect Gong to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-context call analysis with Google ADK

The `get_transcript` tool extracts raw conversational text and feeds it directly into your Google ADK agent. With Gemini's massive context window, your agent can analyze dozens of full call transcripts simultaneously to spot macro trends. This setup bypasses typical token limits, letting you feed hours of sales conversations into a single prompt. The agent uses `list_calls` to fetch historical records and build a complete timeline of customer interactions.

Sync Gong data with your Vertex AI pipelines

The `get_interaction_stats` tool pulls aggregate team metrics into your Google Cloud agent environment. This lets your Google ADK system combine sales performance data with your existing BigQuery data warehouses for deeper operational insights. Your agent can cross-reference these stats with marketing campaigns or product usage data. By executing `list_users`, the agent maps these performance metrics directly to specific sales reps in your organization.

Audit deal conversations using this MCP Server

The `list_trackers` tool retrieves your company's tracked keywords so your Gemini agent can audit sales compliance at scale. The agent scans transcripts for these specific phrases to ensure reps are sticking to the playbook. This MCP Server also exposes `list_scorecards`, allowing the agent to evaluate calls against your official grading criteria. You get automated, objective quality assurance driven directly by your Google Cloud infrastructure.

Setup guide

Set up Gong MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Gong tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Gong_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Gong tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Use McpToolset with StreamableHttpServerParameters pointing to your Vinkius URI. Pass this toolset into your LlmAgent constructor. This exposes all 12 tools, such as search_calls and get_account, to your Gemini-powered agent.

Yes. You can use the optional tool_names filter in the McpToolset configuration to restrict access. For example, you can expose only list_calls and get_transcript while hiding administrative MCP tools.

When your agent invokes get_call_media, the tool returns metadata and URLs for the recording. Google ADK processes this structured response, allowing your agent to reference the media files without hitting payload bottlenecks.

Yes. The list_accounts tool allows your agent to retrieve linked CRM accounts. The agent can then use get_account to pull specific details for any account flagged during transcript analysis.

Your CRM account lists and user metadata fetched via get_user are processed strictly within your Google Cloud boundary. Vinkius handles the authentication token securely, ensuring no credentials or account profiles are exposed to external networks.

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