How to Use the Vidyard MCP in LangChain

Q: How do I query past Vidyard configurations with LangChain?

Your agent can use listvideoplayers to fetch current player names. It then runs these results through the chain, allowing you to ground answers in actual API data from Vidyard.

Q: Can I process video metadata for Vidyard using LangChain?

Yes. You use getvideodetails to pull technical metadata for a specific asset ID. This information is then passed along the chain, letting your agent make decisions based on concrete facts about the video.

Q: What happens if I need to modify Vidyard players with LangChain?

You run getplayerdetails first to validate the player's current state. If the change is approved, the next step in your chain executes updateplayername, making sure the modification happens correctly.

Q: Does Vidyard support deleting assets with LangChain?

It does. For irreversible cleanup steps, you can use deletevideoasset or deletevideoplayer. These are ideal terminal nodes in a complex reasoning chain.

Build complex video workflows and decision chains using Vidyard with LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Vidyard MCP to LangChain

Create your Vinkius account to connect Vidyard 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 Vidyard with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-step asset discovery.

You can list all stored assets first by calling `list_videos`. Then, you run a second step to get specific technical metadata for any video using `get_video_details`. This lets your agent build an accurate sequence. It checks the inventory and gathers required data points before attempting an action like attaching media via `attach_video_to_player`.

Manage multiple player containers.

Need to know what's running? Start by calling `list_video_players` to see all facades. You then get granular details on any specific container using `get_player_details`. If the player needs a new title, you can update it with `update_player_name`. This process of checking state and modifying metadata makes for solid chain steps.

Attach media assets in sequence.

Your agent can check if a target container exists by listing players. If it does, you pass the necessary `player ID` and `video ID` to `attach_video_to_player`. This step links two pieces of data into one functional asset. This chaining ability means your reasoning pipeline handles both finding the components and combining them in a single workflow.

Setup guide

Set up Vidyard 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 Vidyard 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({
    "vidyard-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 Vidyard 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 Vidyard. 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 Vidyard 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 Vidyard MCP in LangChain

Your agent can use `list_video_players` to fetch current player names. It then runs these results through the chain, allowing you to ground answers in actual API data from Vidyard.

Yes. You use `get_video_details` to pull technical metadata for a specific asset ID. This information is then passed along the chain, letting your agent make decisions based on concrete facts about the video.

You run `get_player_details` first to validate the player's current state. If the change is approved, the next step in your chain executes `update_player_name`, making sure the modification happens correctly.

It does. For irreversible cleanup steps, you can use `delete_video_asset` or `delete_video_player`. These are ideal terminal nodes in a complex reasoning chain.

The server touches video asset IDs and player container metadata. When setting up the agent, you control which tools run, ensuring your multi-step pipeline only accesses the specific identifiers needed for the current task.

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