How to Use the Plaud MCP in AutoGen

Q: How do I configure Plaud tools for AutoGen?

Run pip install -U autogen-extmcp. Use mcpservertools with StreamableHttpServerParams to fetch the tools from the MCP Server, then pass them directly into your agent setup.

Q: Can AutoGen agents read my Plaud profile data?

Yes. They can call getme to verify account limits or check which user profile they are currently operating under before running large batch jobs.

Q: How does AutoGen handle Plaud audio downloads?

An agent requests the link via getdownloadurl. Another agent in the chat could then be responsible for taking that URL, downloading the MP3, and pushing it to an external bucket.

Let AutoGen agents debate and organize your Plaud meeting transcripts autonomously.

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 AutoGen

Create your Vinkius account to connect Plaud to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Multi-Agent Plaud Analysis in AutoGen

One agent isn't always enough to parse a complex meeting. You can assign a research agent to pull the text via `get_transcript` and a critic agent to review it. They debate the key takeaways before finalizing anything. The research agent might suggest a summary, but the critic argues it missed a crucial point. They iterate. Once they reach consensus, a third agent updates the record using `update_file`. The MCP Server handles the actual API execution.

Automated Audio Archival Debates

Deleting files is risky. A storage agent scans your account with `list_files` and proposes removing everything older than six months. A compliance agent pushes back, checking `get_file_detail` to ensure no legal meetings get trashed. They negotiate the final list. Once they agree, the storage agent executes `delete_file` on the approved IDs. You get a clean workspace without accidental data loss.

Cross-Referencing Folders and Tags

AutoGen excels at structural organization. Your agents pull the full taxonomy using `list_folders` and `list_tags`. They discuss whether the current tagging system actually makes sense based on the recent summaries from `get_summary`. If they decide a restructure is necessary, they apply the new tags. You just pass the tools to your `AssistantAgent` constructor and let the `McpToolAdapter` handle the schema conversion for the MCP Server.

Setup guide

Set up Plaud MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Plaud tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Plaud_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Plaud data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Plaud_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Plaud data")
    print(result.messages[-1].content)

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 AutoGen

Run `pip install -U autogen-ext[mcp]`. Use `mcp_server_tools` with `StreamableHttpServerParams` to fetch the tools from the MCP Server, then pass them directly into your agent setup.

Yes. They can call `get_me` to verify account limits or check which user profile they are currently operating under before running large batch jobs.

An agent requests the link via `get_download_url`. Another agent in the chat could then be responsible for taking that URL, downloading the MP3, and pushing it to an external bucket.

No. The framework converts everything automatically. Your agents just see the available functions and decide when to use them during their conversation.

Your sensitive MP3 links and meeting summaries never leak. The connection runs inside a strict V8 Isolate Sandbox, ensuring that your authentication tokens and raw text are completely ephemeral.

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