How to Use the Kapwing MCP in AutoGen

Q: How do I initialize the Kapwing tools in AutoGen?

Run pip install -U "autogen-extmcp". Use mcpservertools with your MCP Server URL and pass the resulting tools list directly to your AssistantAgent.

Q: How does AutoGen fix failed Kapwing renders?

If createrender returns an error due to invalid JSON layers, the executing agent reads the error message and debates a fix with the other agents before retrying.

Q: Will AutoGen wait for the Kapwing video to finish?

An agent can be instructed to loop getrenderstatus in the conversation. It will pause its other tasks until it receives the final download URL from the MCP Server.

Deploy multi-agent AutoGen teams to automate Kapwing video production.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kapwing MCP to AutoGen

Create your Vinkius account to connect Kapwing 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 Kapwing with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Negotiate video templates with AutoGen

The `create_render` tool takes a JSON project definition including width, height, and layer configurations to start a media job. In AutoGen, multiple agents debate the structure of this JSON before making the API call. A copywriter agent proposes text layers while a design agent enforces aspect ratio constraints. They iterate on the JSON payload until both agree, ensuring the final tool call won't fail due to invalid dimensions.

Coordinate MCP Server polling tasks

The `get_render_status` tool retrieves the current progress and the final download URL for a specific render ID. You assign one AutoGen agent strictly to monitor this endpoint while others continue working. The monitoring agent polls the API and interrupts the conversation thread when the video hits 100%. A separate reviewer agent then takes the download URL to validate the output against the original prompt.

Audit account usage collaboratively

The `list_renders` tool returns every media asset generated by your account. A finance-focused agent pulls this list to calculate API usage while a content agent reviews the actual videos. They share the data in the group chat. If the finance agent flags high usage, it negotiates with the content agent to reduce the frequency of rendering jobs for the remainder of the session.

Setup guide

Set up Kapwing 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 Kapwing 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="Kapwing_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Kapwing 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="Kapwing_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Kapwing 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 Kapwing. 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 Kapwing 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 Kapwing MCP in AutoGen

Run `pip install -U "autogen-ext[mcp]"`. Use `mcp_server_tools` with your MCP Server URL and pass the resulting tools list directly to your AssistantAgent.

Yes. You can provide the tools to a specific agent in your group chat, allowing it to handle all video generation requests on behalf of the team.

If `create_render` returns an error due to invalid JSON layers, the executing agent reads the error message and debates a fix with the other agents before retrying.

An agent can be instructed to loop `get_render_status` in the conversation. It will pause its other tasks until it receives the final download URL from the MCP Server.

The MCP Server processes project definitions containing exact dimensions and layer text. Vinkius secures this by requiring a single endpoint token and executing the request in an isolated, ephemeral environment that vanishes after use.

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