How to Use the Gong MCP in LangChain

Q: How do I connect the Gong MCP Server to my LangChain agent?

Install langchain-mcp-adapters and initialize the client with your Vinkius endpoint token. Call client.gettools() to load the 14 tools and pass them directly to your agent executor.

Q: Can my LangChain chain run multiple Gong tools in a single execution?

Yes. LangChain allows you to feed the output of listcalls into getcallstats sequentially. The agent decides which tool to call next based on the data returned in the previous step.

Q: How do I verify that the API connection is active?

Run the checkgongstatus tool at the start of your workflow. It returns a simple status check to confirm that your Vinkius credentials are valid and the API is responsive.

Get Gong call transcripts and deal data into your LangChain pipelines using this MCP Server to build automated sales coaching loops.

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 LangChain

Create your Vinkius account to connect Gong to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build multi-step coaching chains with LangChain

Your LangChain agent calls `list_calls_by_user` over this MCP integration to find recent client interactions and feeds the IDs directly into `get_transcript` to extract action items. By linking these tools together in a single chain, you avoid writing boilerplate glue code to pass call data between steps. The agent processes the text, compares it against top-performing patterns, and outputs structured coaching notes. Every step of this chain is visible inside LangSmith, giving you full observability into latency and token usage for each Gong API call.

Map deal risks using LangChain and this MCP Server

This MCP Server exposes `list_deals` to pull active pipelines into your LangChain decision-making pipelines. The agent cross-references these deals against recent call volume with `list_calls_by_date` to flag accounts that are going cold. Instead of manual CRM updates, your agent runs this assessment on a cron job, pulling live data directly from your sales conversations. The output is a prioritized list of high-risk deals backed by actual call activity, ready for your sales managers.

Audit rep performance automatically

The `list_scorecards` tool lets your agent pull the exact grading criteria your managers use to evaluate sales reps. Your LangChain agent uses these scorecards to grade new transcripts retrieved by `get_call` without human intervention. You get objective, consistent scoring across hundreds of calls in minutes. The agent then writes the performance metrics back to your database, updating your team dashboards with fresh data from every single customer call.

Setup guide

Set up Gong MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Gong tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "gong-alternative-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Gong transactions"
    })
    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 LangChain

Install `langchain-mcp-adapters` and initialize the client with your Vinkius endpoint token. Call `client.get_tools()` to load the 14 tools and pass them directly to your agent executor.

Yes. LangChain allows you to feed the output of `list_calls` into `get_call_stats` sequentially. The agent decides which tool to call next based on the data returned in the previous step.

LangChain agents manage rate limits through configurable retries inside your runnables when executing MCP tools. When tools like `get_transcript` hit API limits, the chain pauses and retries based on your backoff settings.

Run the `check_gong_status` tool at the start of your workflow. It returns a simple status check to confirm that your Vinkius credentials are valid and the API is responsive.

All sales call transcripts and user metrics pass through Vinkius's zero-trust, ephemeral V8 sandbox. This MCP setup guarantees no data is stored on Vinkius servers, keeping your sensitive customer conversations completely private.

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