How to Use the Plaud MCP in Pydantic AI

Q: How do I install the Plaud MCP server for Pydantic AI?

Run pip install "pydantic-ai-slimmcp". Use the unified MCPToolset class with your endpoint URL and pass it to your agent.

Enforce strict typing on your Plaud transcripts and summaries using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Plaud MCP to Pydantic AI

Create your Vinkius account to connect Plaud to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Plaud with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Validate Plaud data at runtime

This Plaud toolset stops LLMs from hallucinating JSON fields when reading your transcripts. When connecting this MCP server, Pydantic AI checks the response against your exact data models before the agent can proceed. Your agent calls `get_summary` and gets guaranteed structure back. If the API returns a string where you expected an array of tags, the system throws a loud validation error. No silent corruption makes it into your database. You get exactly the formatting you asked for.

Model-agnostic integration

You are not locked into one specific provider here. The tool execution remains identical across Anthropic, OpenAI, or local models. Your agent uses `list_folders` and `list_files` to navigate your recordings regardless of the underlying brain. Switching models takes one line of code. The MCP standard ensures the inputs and outputs for `update_file` work exactly the same way across the board.

Manage your audio safely

You need reliable execution when modifying user data. If your agent decides to execute `delete_file`, you want absolute certainty it targeted the correct ID. Strict typing guarantees the payload matches the required schema. Need the raw audio? The agent requests `get_download_url` and Pydantic ensures the returned string is actually a valid URL format before passing it down the pipeline.

Setup guide

Set up Plaud 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": {
        "plaud-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Run `pip install "pydantic-ai-slim[mcp]"`. Use the unified `MCPToolset` class with your endpoint URL and pass it to your agent.

Yes. The framework supports both Streamable HTTP and SSE transports natively. Just pass the correct URL format to the toolset.

The framework immediately throws a validation error. It will not allow your agent to process malformed responses from tools like `get_file_detail`.

You can. Pydantic is model-agnostic, meaning you can wire up a local LLM to read your `get_transcript` outputs without hitting external AI APIs.

The server handles raw MP3 URLs and full conversation transcripts. The Vinkius infrastructure processes these payloads within a stateless, zero-trust sandbox that destroys all memory immediately after the tool execution completes.

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