How to Use the Gong MCP in LlamaIndex

Q: How do I index Gong transcripts into a LlamaIndex vector store?

You use the McpToolSpec to fetch transcripts via gettranscript and load them as LlamaIndex Document objects. From there, you can pass them to your vector indexer to make the conversation text fully searchable.

Q: Can I use LlamaIndex to query Gong interaction statistics?

Yes. Your LlamaIndex agent can call getinteractionstats to retrieve raw metrics and format them into structured data. The query engine uses these live stats to answer questions about rep performance.

Q: How do I set up this MCP Server inside my project?

Install the llama-index-tools-mcp package and initialize the BasicMCPClient with your Vinkius endpoint. Then, convert the tools to a list of LlamaIndex-compatible tools using totoollistasync.

Q: Where is our Gong account and user data processed?

All account details from getaccount and user metadata from getuser are processed in memory within the secure Vinkius sandbox. No customer data or PII is cached or stored on the Vinkius platform.

Index Gong transcripts into LlamaIndex vector stores to build RAG pipelines grounded in real sales conversations.

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 LlamaIndex

Create your Vinkius account to connect Gong to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn Gong transcripts into searchable indexes

Do not let your Gong sales data sit idle in a silo when building LlamaIndex applications. This MCP Server allows LlamaIndex to pull raw conversational data using `get_transcript` and convert it into vector embeddings for semantic search. Your LlamaIndex RAG pipeline can then query past customer calls to find exactly how reps handle pricing objections in Gong. The LlamaIndex agent retrieves the actual context from `get_call` instead of making up answers.

Ground LlamaIndex queries in sales metrics

Combine live Gong API data with your static LlamaIndex document stores. LlamaIndex uses `get_interaction_stats` to inject real-time Gong team performance metrics directly into your query engine. When you ask your LlamaIndex agent about team talk ratios, it queries the live Gong API instead of relying on outdated spreadsheets. It pairs this with `list_users` to attribute the Gong performance metrics to the right reps inside your LlamaIndex index.

Build a dynamic sales knowledge base

Keep your product marketing teams aligned with actual customer feedback using this MCP integration in LlamaIndex. LlamaIndex queries `list_trackers` to find which feature requests are trending in Gong and indexes those terms alongside your product specs. The LlamaIndex index updates dynamically by calling `list_calls` to ingest new Gong meetings daily. This ensures your LlamaIndex Q&A bots always use the latest customer feature requests from Gong.

Setup guide

Set up Gong MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Gong MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Gong tools.",
)
response = await agent.run("List recent Gong data")

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 LlamaIndex

You use the `McpToolSpec` to fetch transcripts via `get_transcript` and load them as LlamaIndex Document objects. From there, you can pass them to your vector indexer to make the conversation text fully searchable.

Yes. Your LlamaIndex agent can call `get_interaction_stats` to retrieve raw metrics and format them into structured data. The query engine uses these live stats to answer questions about rep performance.

Yes. You can configure your agent to use the MCP tool to query `list_accounts` for the correct CRM ID, then pass that ID to `search_calls` to retrieve and index only the calls associated with that specific client.

Install the `llama-index-tools-mcp` package and initialize the `BasicMCPClient` with your Vinkius endpoint. Then, convert the tools to a list of LlamaIndex-compatible tools using `to_tool_list_async`.

All account details from `get_account` and user metadata from `get_user` are processed in memory within the secure Vinkius sandbox. No customer data or PII is cached or stored on the Vinkius platform.

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