How to Use the Fliki (AI Text-to-Video & Speech API) MCP in OpenAI Agents SDK

Q: How do I initialize the Fliki (AI Text-to-Video & Speech API) server inside the OpenAI Agents SDK?

Install the SDK and use MCPServerStreamableHttp to point to the server endpoint. Pass the server instance inside the mcpservers list when instantiating your agent.

Q: Can my agent choose different speakers using Fliki (AI Text-to-Video & Speech API) and OpenAI Agents SDK?

Yes, your agent can call listvoices to find available speakers. It then feeds the selected voice ID directly into the generatevideo parameters.

Q: How does the OpenAI Agents SDK handle rendering timeouts with the Fliki (AI Text-to-Video & Speech API) MCP Server?

Your agent should run a polling loop that calls getvideo to check the progress. The SDK's tracing dashboard lets you monitor these status checks to ensure the loop doesn't run indefinitely.

Q: How do I cache tool definitions to speed up my agent?

Set cacheToolsList=True when configuring your server stream. This prevents the SDK from querying the MCP server for its tool definitions on every single execution loop.

Turn raw text scripts into fully rendered videos directly from your OpenAI Agents SDK pipeline with automatic tool discovery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fliki (AI Text-to-Video & Speech API) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Fliki (AI Text-to-Video & Speech API) to OpenAI Agents SDK 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 Fliki (AI Text-to-Video & Speech API) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Video Pipelines with OpenAI Agents SDK

Let your specialized OpenAI agents handle the entire video production pipeline from writing scripts to rendering. Your agent uses `generate_video` to pass scripts, aspect ratios, and background music directly to the API, then hands off the task to a monitoring agent to wait for the final asset. The SDK handles tool discovery automatically. By using this MCP Server, your pipeline runs with built-in OpenAI guardrails that validate agent arguments before making API calls, keeping costs completely under control.

Dynamic Voice Selection via `list_voices`

Stop hardcoding voice options in your agent system. This tool lets your agent call `list_voices` to inspect available voice profiles dynamically, allowing the system to match the exact vocal tone to the content of your script on the fly. You can trace these voice selection calls directly in your OpenAI dashboard. Setting `cacheToolsList=True` ensures your agents don't waste time fetching the tool schema repeatedly on every turn.

Async Rendering Status Tracking

Video generation takes time, and blocking your main agent loop is a terrible idea. Your agent uses `get_video` to poll the rendering status asynchronously, checking if the file is ready for download while freeing up execution threads. Combine this with the SDK's native async context manager to connect to this MCP Server cleanly. The `MCPServerStreamableHttp` client manages the HTTP connection under the hood, ensuring your agents get clean status updates without manual network code.

Setup guide

Set up Fliki (AI Text-to-Video & Speech API) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Fliki (AI Text-to-Video & Speech API) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Fliki (AI Text-to-Video & Speech API) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Fliki (AI Text-to-Video & Speech API) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Fliki (AI Text-to-Video & Speech API) Agent",
            instructions="You have access to Fliki (AI Text-to-Video & Speech API) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Fliki. 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 Fliki (AI Text-to-Video & Speech API) 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 Fliki (AI Text-to-Video & Speech API) MCP in OpenAI Agents SDK

Install the SDK and use `MCPServerStreamableHttp` to point to the server endpoint. Pass the server instance inside the `mcp_servers` list when instantiating your agent.

Yes, your agent can call `list_voices` to find available speakers. It then feeds the selected voice ID directly into the `generate_video` parameters.

Your agent should run a polling loop that calls `get_video` to check the progress. The SDK's tracing dashboard lets you monitor these status checks to ensure the loop doesn't run indefinitely.

Set `cacheToolsList=True` when configuring your server stream. This prevents the SDK from querying the MCP server for its tool definitions on every single execution loop.

Your text scripts, voice profiles, and output video URLs are processed inside a secure V8 Isolate Sandbox. Vinkius handles the API token authentication on a single secure endpoint, ensuring your raw text payloads are never exposed to third-party networks.

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