How to Use the Deepgram MCP in Pydantic AI

Q: How does Pydantic AI validate Deepgram tool outputs?

The framework intercepts JSON responses from tools like transcribeaudiourl and validates them against internal Pydantic models. If there is a schema mismatch, it raises a validation error instead of passing dirty data to your model.

Q: How do I configure the Deepgram MCP connection in Pydantic AI?

Use the unified MCPToolset class pointing to your HTTP server URL. Pass this toolset directly into your Agent's toolsets list, avoiding the deprecated HTTP server classes.

Q: What happens if a Deepgram API key check fails during runtime?

When calling listapikeys, any authorization error is caught and raised as a standard validation exception. This allows your application to handle expired keys gracefully without crashing the process.

Build type-safe voice apps with Pydantic AI and this Deepgram MCP Server, validating every transcript at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deepgram MCP to Pydantic AI

Create your Vinkius account to connect Deepgram 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 Deepgram with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict Runtime Validation for Pydantic AI

Stop letting malformed API responses break your voice applications. This MCP Server ensures that every output from `transcribe_audio_url` is strictly validated against Pydantic schemas before your agent even reads the text. If the speech service returns an unexpected format, the framework fails loudly and immediately. This prevents bad transcript data from corrupting downstream database writes or agent decisions.

Type-Safe Voice Synthesis Configuration

Generate speech with complete confidence in your parameters. When your agent calls `convert_text_to_speech`, the input text and voice settings are checked against strict Python types at runtime. This MCP configuration eliminates silent failures where a model hallucinated a voice name or passed an invalid speed setting, ensuring your audio outputs are always clean.

Structured Usage and Model Auditing

Keep your system configuration clean by validating project details. The agent uses `list_deepgram_projects` and `get_project_usage` to verify account status, returning typed models that your application can safely parse. Instead of dealing with raw JSON dictionaries, your code receives structured data when checking `list_available_models`, making it simple to filter active speech models programmatically.

Setup guide

Set up Deepgram 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": {
        "deepgram-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Deepgram 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 Deepgram. 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 Deepgram 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 Deepgram MCP in Pydantic AI

The framework intercepts JSON responses from tools like `transcribe_audio_url` and validates them against internal Pydantic models. If there is a schema mismatch, it raises a validation error instead of passing dirty data to your model.

Yes, the framework is completely model-agnostic. You can run `convert_text_to_speech` using OpenAI, Anthropic, Gemini, or even a local model while maintaining the exact same type-safety guarantees.

Use the unified `MCPToolset` class pointing to your HTTP server URL. Pass this toolset directly into your Agent's toolsets list, avoiding the deprecated HTTP server classes.

When calling `list_api_keys`, any authorization error is caught and raised as a standard validation exception. This allows your application to handle expired keys gracefully without crashing the process.

Your credentials and transcripts are handled inside ephemeral sandboxes that dissolve immediately after execution. No audio data or transcription text is ever cached or logged on Vinkius infrastructure.

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