How to Use the GAN.ai MCP in LlamaIndex

Q: How do I get started with the GAN.ai MCP server and LlamaIndex?

It's direct. Install the llama-index-tools-mcp package, create a BasicMCPClient with your Vinkius endpoint URL, and then use McpToolSpec to load the GAN.ai tools into your agent.

Turn your GAN.ai video campaign history into a searchable knowledge base with LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GAN.ai MCP to LlamaIndex

Create your Vinkius account to connect GAN.ai 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 GAN.ai with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Video Campaign Activity

LlamaIndex makes tool outputs part of your agent's memory. When your agent calls `list_generated_videos` or `list_video_projects`, the results are automatically indexed. This creates a living document of all your marketing campaigns. You can then ask questions in plain English, like 'show me all the videos we generated for the Q3 campaign.' The agent queries the index, which is grounded in actual data retrieved from GAN.ai tools like `get_video_stats`, so you get facts, not guesses.

Build RAG Apps on Live Video Data

This is more than just calling tools; it's about augmenting your agent's knowledge with real-time information. You can build a query engine that combines your internal marketing documents with live data from the GAN.ai MCP server. For example, ask your LlamaIndex agent: 'Summarize the performance of our top 3 video templates this quarter.' The agent can use `list_video_projects` to find the templates, call `get_video_stats` for each, and then synthesize a report based on that live API data.

Ground Agent Decisions in Factual Data with LlamaIndex

An agent without memory makes the same mistakes twice. By indexing the output of tools like `get_generation_status`, your agent learns which campaigns had rendering issues. It builds a factual history of what works and what doesn't. Before launching a new campaign, the agent can query its own index about past API health by reviewing the history of calls to `verify_api_connection`. This lets it make smarter decisions, like picking a different video template if a similar one failed before. This MCP setup is about building institutional knowledge.

Setup guide

Set up GAN.ai 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 GAN.ai 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 GAN.ai tools.",
)
response = await agent.run("List recent GAN.ai 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 GAN.ai. 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 GAN.ai 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 GAN.ai MCP in LlamaIndex

LlamaIndex can be configured to automatically index the JSON output from any GAN.ai tool call. This means data from `list_generated_videos` or `get_video_stats` becomes part of a vector index you can query with natural language.

Yes. After your agent has run campaigns and indexed the results, you can ask questions like 'find the video for contact@example.com from last week.' LlamaIndex will search the indexed output of `list_generated_videos` to find the exact match.

That's exactly what it's built for. You can create a single query engine that indexes both your internal strategy documents and live data from the GAN.ai MCP Server. This gives your agent full context for its decisions.

It's direct. Install the `llama-index-tools-mcp` package, create a `BasicMCPClient` with your Vinkius endpoint URL, and then use `McpToolSpec` to load the GAN.ai tools into your agent.

The server processes any personalization data you send to it, like names or other text variables for the `generate_single_video` tool. Your data is handled within a zero-trust environment on Vinkius. Each API call is a discrete, sandboxed operation that doesn't persist your inputs on the server.

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