How to Use the api.video MCP in AutoGen

Q: Can I create an AutoGen workflow where one agent creates an api.video video and another approves it?

Absolutely. You can have a 'Creator' agent call createvideoobject, then pass the video ID to an 'Approver' agent. The Approver can use getvideodetails to check the work before the video is made public.

Q: How do I give different AutoGen agents access to different api.video tools?

When you configure each AssistantAgent, you pass a specific list of tools to its constructor. This lets you restrict one agent to only use listvideos while another has access to deletevideo.

Q: What's the process for connecting my AutoGen agents to the api.video MCP server?

You use the mcpservertools function from the AutoGen extension, passing it your Vinkius server URL. This returns a list of tools that you can then provide to your AssistantAgent during initialization.

Let your AutoGen agents debate and manage your api.video library through multi-agent conversation.

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 AutoGen

Create your Vinkius account to connect api.video to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn video management into a debate

Assign specialized roles to your agents. A 'Content Auditor' agent can use `list_videos` to find old content and propose deletions. It then presents its findings to a 'Legal' agent, which uses `get_video_details` to check for compliance holds before approving the `delete_video` call. AutoGen turns a simple task into a robust, conversational workflow. Actions are taken based on a consensus between agents, not a single command.

Let agents collaborate on content updates

Have a 'Creative' agent propose a new, more engaging title for a video. It uses the `update_video_details` tool to stage the change. A 'Brand Voice' agent can then review the suggestion, and the two can discuss it until they agree. This back-and-forth is what makes AutoGen different. The final update is only executed after your specialized agents come to an agreement, catching potential issues before they happen.

Use your MCP Server for multi-agent analysis

Set up a team of agents to analyze your video performance. An 'Analytics' agent calls `get_video_analytics` to report on view counts, while a 'UX' agent calls `list_player_themes` to check for brand consistency on the same videos. These agents can then debate their findings in a shared chat. They can argue whether a drop in views is due to the content itself or a poorly configured player, with each agent bringing its own data to the table.

Setup guide

Set up api.video MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes api.video tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="api.video_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent api.video data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="api.video_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent api.video data")
    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 AutoGen

Absolutely. You can have a 'Creator' agent call `create_video_object`, then pass the video ID to an 'Approver' agent. The Approver can use `get_video_details` to check the work before the video is made public.

When you configure each `AssistantAgent`, you pass a specific list of tools to its constructor. This lets you restrict one agent to only use `list_videos` while another has access to `delete_video`.

You use the `mcp_server_tools` function from the AutoGen extension, passing it your Vinkius server URL. This returns a list of tools that you can then provide to your `AssistantAgent` during initialization.

Yes, that's a perfect use case. You can create an 'Analyst' agent with access to `get_video_analytics` and a 'Strategist' agent. The Analyst provides data, and the Strategist interprets it, debating the next steps in chat.

The server processes requests for video metadata, analytics, and settings, but your data is not stored. Vinkius uses zero-trust, ephemeral containers for each tool call, which keeps the conversations between your AutoGen agents and the data they access private and isolated.

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