How to Use the Shotstack MCP in AutoGen

Q: How do I manage video creation using Shotstack and AutoGen?

You set up multiple agents: one 'Creator' that runs rendervideo, and another 'Validator' agent that uses listassetsfromrender to ensure all expected output files are present before the final sign-off.

Q: Can I verify template readiness using Shotstack and AutoGen?

Absolutely. An agent can call listtemplates, and another can compare that list against the required components, ensuring all necessary templates are available before starting a complex rendering job.

Q: If I build an autonomous system with Shotstack and AutoGen, how does it work?

You define roles. One agent acts as the 'Planner,' calling listrecentrenders to see history; a second 'Executor' then uses that data to call getrenderstatus for active jobs.

Facilitate consensus decisions on video pipelines using AutoGen's multi-agent debate with the Shotstack MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Shotstack MCP to AutoGen

Create your Vinkius account to connect Shotstack to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Shotstack with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Debate render requirements with the MCP Server

One agent can propose a complex workflow by calling `render_video` and generating an ID. A second 'Review' agent, armed with `get_render_status`, then debates whether that job is actually finished or if it’s still pending. This consensus-driven process confirms the final state of the content before moving forward. Agents can challenge each other on resource needs by checking available sources using `list_ingested_sources`.

Cross-check asset availability and templates

In a debate scenario, one agent might suggest a new video style, triggering the need for a template. Another agent can respond by calling `list_templates` to confirm if that blueprint exists. If not, they must collaboratively decide on whether to use `create_video_template` or abort. The conversation ensures all necessary inputs are verified against `list_hosted_assets` before committing resources.

Build structured content pipelines with the Shotstack MCP Server

The AutoGen framework lets you build multi-step reasoning where one agent initiates a job using `ingest_media_source`, and another tracks its success by periodically calling `get_render_status`. This collaborative loop ensures that no step is skipped, and the final decision relies on verified status updates. This makes your system reliable when dealing with asynchronous operations.

Setup guide

Set up Shotstack 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 Shotstack 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="Shotstack_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You set up multiple agents: one 'Creator' that runs `render_video`, and another 'Validator' agent that uses `list_assets_from_render` to ensure all expected output files are present before the final sign-off.

The server deals with media assets and render metadata. The sensitive data points include source file types, user credentials used for API calls, and generated content IDs from tools like `render_video`.

Absolutely. An agent can call `list_templates`, and another can compare that list against the required components, ensuring all necessary templates are available before starting a complex rendering job.

You define roles. One agent acts as the 'Planner,' calling `list_recent_renders` to see history; a second 'Executor' then uses that data to call `get_render_status` for active jobs.

The agents can debate the issue. For example, one agent notes a discrepancy between `list_ingested_sources` and what is needed for the render, and they negotiate a fix before proceeding.

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