How to Use the CAMB.AI MCP in OpenAI Agents SDK

Q: Can the OpenAI Agents SDK track CAMB.AI dubbing jobs?

Yes. Your agent uses the getjobstatus tool to check progress. Because OpenAI traces agent actions, you can view the polling frequency and response times directly in your dashboard.

Q: Will OpenAI Agents SDK validate CAMB.AI voice clones?

The SDK applies guardrails before executing the createvoiceclone tool. You define constraints that ensure the agent only passes valid audio file references. This stops bad requests from reaching the server.

Build production-grade audio translation pipelines using OpenAI Agents SDK. Connect CAMB.AI to dub videos with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CAMB.AI MCP to OpenAI Agents SDK

Create your Vinkius account to connect CAMB.AI 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 CAMB.AI with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Voice Cloning with OpenAI Guardrails

Your agent needs to clone a specific speaker before running translation tasks. By giving the OpenAI Agents SDK access to the `create_voice_clone` tool, it pulls reference audio and registers a custom voice profile. The built-in guardrails validate the audio format before execution, preventing failed API calls. Once registered, your agent checks available profiles using `list_cloned_voices`. You can then configure a specialized dubbing agent to hand off tasks, ensuring the right cloned voice matches the original speaker across your entire media library. This MCP Server handles the audio processing while OpenAI tracks every step in the dashboard.

Automated Dubbing Pipelines

Translating media across multiple languages requires precise task tracking. Your agent triggers `create_dubbing` to start the process, mapping source audio to target regions. It automatically pulls valid options via `list_source_languages` and `list_target_languages` so it never guesses supported dialects. Handoffs make this powerful. One agent starts the dubbing job, and another specialized agent polls `get_job_status` until completion. This MCP integration keeps your main conversational agent free to handle user requests instead of waiting on long-running audio generation tasks.

Text-to-Speech via MCP Server

Generating audio directly from text prompts is a core feature of this integration. The agent calls `create_tts` with a specific script and voice ID. Because OpenAI Agents SDK traces every action, you see exactly which text went into the prompt and how long the generation took. After initiating the request, the system monitors progress through `get_tts_status`. When the audio finishes processing, the agent fetches the final file location using `get_tts_result`. You get production-ready voiceovers without writing custom polling scripts.

Setup guide

Set up CAMB.AI 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 CAMB.AI tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives CAMB.AI tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate CAMB.AI 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="CAMB.AI Agent",
            instructions="You have access to CAMB.AI 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 CAMB.AI. 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 CAMB.AI 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 CAMB.AI MCP in OpenAI Agents SDK

Install the openai-agents package first. You initialize MCPServerStreamableHttp with your Vinkius endpoint url and pass it into the mcp_servers array on your Agent constructor. Set cacheToolsList=True so your agent discovers the dubbing tools faster.

Yes. Your agent uses the get_job_status tool to check progress. Because OpenAI traces agent actions, you can view the polling frequency and response times directly in your dashboard.

It provides ten specific operations for audio processing. Your agent can call create_dubbing, create_tts, and list_voices to generate speech. It also includes status checkers like get_tts_result to fetch completed files.

The SDK applies guardrails before executing the create_voice_clone tool. You define constraints that ensure the agent only passes valid audio file references. This stops bad requests from reaching the server.

Your source audio files and generated voice clones stay protected. Vinkius runs the connection through a V8 Isolate Sandbox that destroys the environment after your session ends. Zero-trust architecture means your proprietary media never sits exposed on a persistent server.

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