How to Use the Plaud MCP in OpenAI Agents SDK

Q: How do I install the Plaud MCP server for OpenAI Agents SDK?

Run pip install openai-agents first. Then initialize MCPServerStreamableHttp with your endpoint URL and pass it to your agent's mcpservers list.

Q: Why is my Plaud agent running slow in OpenAI Agents SDK?

You likely forgot to enable caching. Pass cacheToolsList=True when configuring the MCP server connection so the agent doesn't fetch the schema on every single turn.

Q: Does the integration support audio downloads?

It does. The getdownloadurl tool returns a direct link to the MP3. Your agent can then hand that URL off to another service if needed.

Connect Plaud to your OpenAI Agents SDK setup to audit meeting transcripts and extract summaries in production.

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 OpenAI Agents SDK

Create your Vinkius account to connect Plaud to OpenAI Agents SDK — 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Build multi-agent pipelines for Plaud

This Plaud integration gives your agent the raw meeting data it needs to do its job. Hand it the `get_transcript` tool so it can pull down exactly what was said during your last standup. You don't have to write custom API wrappers because the MCP standard auto-discovers all ten available operations. Set `cacheToolsList=True` to keep things fast. Once connected, your primary router agent can hand off specific tasks. Have one agent run `get_summary` while another tags the recording using `update_file`.

Trace every MCP Server action

Production systems require visibility. When your Python script executes `delete_file` or `get_download_url`, the OpenAI dashboard logs the exact request and response. You see exactly why an agent decided to dump a specific recording. Guardrails matter here. You can set strict boundaries on what the agent is allowed to touch. If it tries to wipe an entire directory instead of a single MP3, the framework catches the violation before the HTTP request ever fires.

Organize your audio vault

Managing hundreds of voice memos gets messy quickly. Give your agent access to `list_folders` and `list_tags` to map out the current structure. From there, it can read the metadata via `get_file_detail` and figure out what belongs where. The real value is automation. An agent can pull the transcript, decide the current tags are completely wrong, and fix them on the fly. You just let it run in the background.

Setup guide

Set up Plaud MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Plaud tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Plaud tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Plaud tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Plaud Agent",
            instructions="You have access to Plaud tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Run `pip install openai-agents` first. Then initialize `MCPServerStreamableHttp` with your endpoint URL and pass it to your agent's `mcp_servers` list.

Yes. The framework auto-discovers the schema. You just provide the server connection and tools like `list_files` populate instantly.

You likely forgot to enable caching. Pass `cacheToolsList=True` when configuring the MCP server connection so the agent doesn't fetch the schema on every single turn.

It does. The `get_download_url` tool returns a direct link to the MP3. Your agent can then hand that URL off to another service if needed.

The server processes raw meeting transcripts and audio summaries. Vinkius isolates this execution inside a zero-trust V8 sandbox, meaning your MP3s and text payloads are never stored on disk after the session ends.

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