How to Use the api.video MCP in LangChain

Q: How do I make a LangChain agent find and delete a specific api.video video?

You'd build a chain where the agent first uses listvideos with a title filter to find the video's ID. Then, it passes that ID to the deletevideo tool in the next step.

Q: Can LangChain use api.video to get analytics and then summarize the data?

Yes. Your agent can call getvideoanalytics to get the raw numbers. You then chain that output to a model that is prompted to summarize the performance data into a short report.

Q: Can I filter my videos by tags when using this server?

Yes, the listvideos tool supports filtering by tags. Your agent can specify one or more tags to narrow down the list of videos it's working with.

Build agents that manage your entire video library using LangChain and the api.video MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect api.video MCP to LangChain

Create your Vinkius account to connect api.video 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 api.video with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain video operations together

Build agents that perform multi-step video tasks. Your agent can initialize a new video with `create_video_object`, then immediately use the returned ID to modify its metadata with `update_video_details` in the next step of the chain. This isn't just about single actions. You can design complex logic, like having an agent call `list_videos` with a specific tag, then pass that list to `delete_video` to automatically clean up old content. It's all one fluid operation.

Feed live video data into reasoning loops

Use tools like `list_videos` and `get_video_details` to give your agents a real-time view of your media library. Your agent can pull this data into its reasoning process to decide what to do next. And because you're using LangChain, you get full observability through LangSmith. You can trace exactly how your agent uses the api.video tools, seeing every input, output, and latency spike. It makes debugging complex chains much simpler.

Combine video analytics with other tools

This MCP Server makes api.video just another tool in your agent's toolbox. Have your agent pull performance data for a specific video using `get_video_analytics`. Then, in the same chain, it can pass those metrics to a completely different tool—one that writes a report to a database, sends a Slack alert, or even generates a new title suggestion. Your agent decides how to connect the dots.

Setup guide

Set up api.video 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 api.video 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({
    "apivideo-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 api.video 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 api.video. 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 api.video 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 api.video MCP in LangChain

You'd build a chain where the agent first uses `list_videos` with a title filter to find the video's ID. Then, it passes that ID to the `delete_video` tool in the next step.

Yes. Your agent can call `get_video_analytics` to get the raw numbers. You then chain that output to a model that is prompted to summarize the performance data into a short report.

First, install the MCP adapter. Then, you'll instantiate the `MultiServerMCPClient` with your Vinkius endpoint URL. Call `client.get_tools()` and pass the resulting tool list to your agent.

Yes, the `list_videos` tool supports filtering by tags. Your agent can specify one or more tags to narrow down the list of videos it's working with.

No. The server only handles requests for your video metadata, analytics, and account settings. All tool calls are proxied through Vinkius's ephemeral sandboxes, so your agent's logic and the data it processes are isolated and not stored.

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