How to Use the AssemblyAI MCP in Pydantic AI

Q: Can Pydantic AI validate the output from AssemblyAI sentiment analysis?

Yes. When the agent calls getsentiments, Pydantic AI checks the returned JSON against your predefined models. Any missing sentiment scores trigger an immediate validation error.

Q: What happens if the transcription fails?

The gettranscript tool returns the error status. Pydantic AI catches this and forces the agent to handle the specific failure state defined in your types.

Get strongly-typed audio transcripts and sentiment analysis in Pydantic AI with the AssemblyAI MCP integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AssemblyAI MCP to Pydantic AI

Create your Vinkius account to connect AssemblyAI 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 AssemblyAI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe transcription with an MCP Server

Pydantic AI demands strict data structures, and this integration delivers exactly that. Your agent submits a file using `transcribe_audio_url`. When it calls `get_transcript` to retrieve the text, the framework validates the response against your Pydantic models at runtime. If the API returns missing fields, the agent fails loudly. You never get silent corruption or hallucinated text creeping into your database. It works flawlessly across Claude, GPT-4, and local Llama models.

Type-checked speaker and topic extraction

Extracting metadata from audio through this MCP Server requires precision. The agent hits `get_speakers` to map out the conversation flow. Every speaker label and timestamp gets checked against your schema before your application processes it. The same strict rules apply to content analysis. When your agent runs `get_topics` or `get_chapters`, Pydantic AI ensures the arrays and strings match your exact definitions. You build reliable audio pipelines that break early if the data format shifts.

Strict control over transcription history

Managing past jobs is just as rigorous. Your agent pulls recent records via `list_transcripts` to audit your account usage. The framework guarantees the returned list structure matches your expectations. Deleting files happens through `delete_transcript`. Because Pydantic AI validates the inputs, your agent will not accidentally send a malformed ID and delete the wrong recording. You delete exactly what you intend to.

Setup guide

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

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

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

Use the unified MCPToolset class pointing to your Vinkius HTTP endpoint. Pass that into your Agent toolsets array. The agent will read and validate the tool schemas automatically.

Yes. When the agent calls `get_sentiments`, Pydantic AI checks the returned JSON against your predefined models. Any missing sentiment scores trigger an immediate validation error.

It works perfectly. Pydantic AI is model-agnostic. You can route the `get_summary` output through a local model running on your own hardware.

The `get_transcript` tool returns the error status. Pydantic AI catches this and forces the agent to handle the specific failure state defined in your types.

This MCP Server touches audio URLs, speaker transcripts, and topic arrays. Vinkius runs the connection through an ephemeral sandbox that destroys itself after the run. No persistent storage means your proprietary voice data cannot leak.

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