How to Use the GAN.ai MCP in LangChain

Q: Can my agent monitor a video generation job?

Yes. You create a loop in your chain that repeatedly calls getgenerationstatus with the job ID. The agent can wait until the status is 'complete' before moving to the next step, like fetching stats with getvideostats.

Build video generation pipelines and let your LangChain agent run the show, from creation to analytics.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Automated Video Workflows

This isn't about one-off tasks. It's about building a complete, automated chain. Your LangChain agent can start by calling `list_video_projects` to find the right template, then feed a list of contacts into `generate_personalized_videos` to kick off a bulk job. Once the job is running, the agent doesn't just sit there. It can enter a loop, periodically calling `get_generation_status` to check on progress. When the videos are done, it automatically pulls engagement data using `get_video_stats`. You're building a full-cycle campaign that runs itself.

Create Self-Healing Campaign Agents with LangChain

A script breaks when an API fails. A good agent adapts. Before starting a big job, your agent can use `verify_api_connection` to make sure GAN.ai is reachable. It's a simple check that prevents a lot of problems. This approach makes your campaigns far more reliable. The agent can query `get_workspace_info` to check your account's limits before trying to generate thousands of videos with `generate_personalized_videos`. That's the whole point of giving an agent these tools—it can reason and react, not just execute.

Connect Video Data to Other Systems

LangChain's real strength is connecting different services. You can build a chain that pulls new leads from a Salesforce database, runs each one through GAN.ai's `generate_single_video` tool, and then posts the unique video URL to a team Slack channel. And the data flows both ways. The output from `get_video_stats` doesn't have to die in a log file. With this MCP server, your agent can take that engagement data and push it directly into a CRM or data warehouse, closing the loop between a video view and your sales process.

Setup guide

Set up GAN.ai 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 GAN.ai 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({
    "ganai-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 GAN.ai 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 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 LangChain

First, get the tools list from the MCP client and pass it to your agent executor. The agent then uses the tool descriptions to decide the sequence, like calling `list_video_projects` first, then `generate_personalized_videos`. LangChain handles passing the output of one step as the input for the next.

Yes. You create a loop in your chain that repeatedly calls `get_generation_status` with the job ID. The agent can wait until the status is 'complete' before moving to the next step, like fetching stats with `get_video_stats`.

Use a ReAct agent. This lets the agent see an error from a tool like `generate_personalized_videos`, think about it, and decide to call `verify_api_connection` or simply retry the operation. It's much more resilient than a simple script.

Absolutely. The agent can be prompted with a goal, like 'create a Q4 promo video.' It can then call `list_video_projects`, review the available templates, and select the best one based on names or metadata before generating any videos.

The server primarily handles personalization data you provide to tools like `generate_personalized_videos`, such as recipient names or company details. Vinkius isolates each request in an ephemeral sandbox. Your connection is authenticated via a single token, and the MCP server itself doesn't store your data after the job is complete.

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