How to Use the 3Scribe MCP in Pydantic AI

Q: What happens if the 3Scribe API returns an unexpected format to my Pydantic AI agent?

Your agent will fail immediately and loudly with a ValidationError. This is the core benefit of Pydantic AI: it prevents data corruption by refusing to process any data that doesn't conform to your predefined models.

Q: How do I start a transcription job from a URL?

Your agent needs to call the createjob tool, passing the public URL of the media file as a parameter. It will return a job ID which you can then use with getjob to check the status and get the text.

Add type-safe audio transcription to your Pydantic AI agent. Get structured, validated text from any media file that matches your Pydantic models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 3Scribe MCP to Pydantic AI

Create your Vinkius account to connect 3Scribe 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 3Scribe with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Validated Transcription Output

Your agent calls `create_job` with a media URL to start a transcription. 3Scribe does the work and gives you back a job ID. When your agent calls `get_job`, Pydantic AI automatically validates the response. If the job status or text doesn't match your Pydantic model, it raises a `ValidationError`. No more silent failures or parsing messy, unexpected JSON.

Reliably Manage Transcription History

Use the `list_jobs` tool to get a history of your transcriptions. Pydantic AI ensures the list of jobs it receives is correctly formatted. You can trust that every item in the list is a valid job object. When you use `delete_job`, you know for sure that the confirmation response is what you expect. This focus on correctness means your agent won't get confused by an odd API reply when performing a destructive action. It either works correctly, or it fails loudly.

Your Type-Safe Transcription MCP Server

This MCP server integrates cleanly with Pydantic AI. After the `pip install`, you just create an `MCPToolset` instance pointing to your Vinkius server URL. It's the modern, unified way to add tools. Pass that toolset to your `Agent`. Pydantic AI handles the rest, making sure every call to `create_job` or `get_job` results in data that perfectly fits your defined models. It works with any LLM you plug in.

Setup guide

Set up 3Scribe 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": {
        "3scribe-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to 3Scribe tools.",
)

result = await agent.run("List recent 3Scribe 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 3Scribe. 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 3Scribe 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 3Scribe MCP in Pydantic AI

Pydantic AI validates every response from the 3Scribe server against your Pydantic models at runtime. If the API returns data that doesn't match the expected structure—like a missing field—it will raise a `ValidationError` instead of letting your agent process bad data.

Your agent will fail immediately and loudly with a `ValidationError`. This is the core benefit of Pydantic AI: it prevents data corruption by refusing to process any data that doesn't conform to your predefined models.

Yes. Pydantic AI is model-agnostic, so you can use this 3Scribe toolset with agents powered by OpenAI, Anthropic, Gemini, or even local models. The validation happens within the Pydantic AI framework, independent of the LLM.

Your agent needs to call the `create_job` tool, passing the public URL of the media file as a parameter. It will return a job ID which you can then use with `get_job` to check the status and get the text.

The server only sees the media URLs you send and the transcription text it generates. All communication is encrypted. Vinkius isolates each MCP server in its own ephemeral instance, which is destroyed after use, ensuring your transcription data isn't persisted on the 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