How to Use the CAMB.AI MCP in Pydantic AI

Q: How do I configure the CAMB.AI MCP Server with Pydantic AI?

Install the pydantic-ai-slimmcp package. You initialize an MCPToolset using your Vinkius HTTP endpoint URL. Pass this unified toolset into your Agent constructor so it can access the dubbing functions.

Build type-safe audio dubbing agents with the CAMB.AI MCP Server and Pydantic AI. Validate every response at runtime to prevent silent failures.

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 Pydantic AI

Create your Vinkius account to connect CAMB.AI to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Audio Dubbing

Generating multilingual audio requires exact parameters. When your Pydantic AI agent calls `create_dubbing`, it expects a specific response structure containing the job ID. If the API returns unexpected fields, the framework fails loudly with a validation error. You never get silent corruption in your audio pipelines. Polling for completion is just as strict. The agent uses `get_job_status` to check the translation progress. Because every output gets validated against your Pydantic models, you know exactly when the file is ready without writing custom retry scripts. This MCP Server integration prioritizes absolute correctness.

Validated Voice Cloning

Creating custom speaker identities demands precision. Your agent triggers `create_voice_clone` and immediately validates the returned voice ID. It then cross-references the new profile by running `list_cloned_voices` to ensure the registration succeeded. Swapping underlying LLMs won't break your audio logic. You can run an Anthropic or local model while interacting with these cloning tools exactly the same way. The type-safety guarantees the inputs match what the server expects.

Text-to-Speech with Pydantic AI

Converting scripts to audio via MCP introduces potential formatting issues. The agent pulls available options via `list_voices` and validates the selected voice ID before starting the job. It then calls `create_tts` to generate the speech file. Fetching the final asset requires two strict steps. The agent monitors the process with `get_tts_status` until it receives a success state. It then executes `get_tts_result` to grab the download link, guaranteeing the URL structure matches your predefined schema.

Setup guide

Set up CAMB.AI MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "cambai-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to CAMB.AI tools.",
)

result = await agent.run("List recent CAMB.AI transactions")
print(result.output)

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 Pydantic AI

Install the pydantic-ai-slim[mcp] package. You initialize an MCPToolset using your Vinkius HTTP endpoint URL. Pass this unified toolset into your Agent constructor so it can access the dubbing functions.

Strict runtime validation prevents hallucinated audio parameters. If the agent tries to pass an invalid language code to create_dubbing, the framework stops it immediately. You avoid wasting money on failed generation attempts.

Yes, the framework handles this natively. When the agent calls list_voices or list_cloned_voices, the response gets checked against your expected models. Missing fields trigger immediate errors instead of breaking downstream logic.

Yes, the framework is completely model-agnostic. You can connect a local Llama model to the MCP Server tools like get_tts_result. The Pydantic validation ensures the local model formats the audio requests correctly.

Translated video files and custom speech generations stay completely private. Authentication happens through a single endpoint token that connects to a zero-trust V8 sandbox. No external parties can intercept your proprietary media during the generation process.

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