How to Use the Plaud MCP in Google ADK

Q: How do I configure the Plaud MCP server with Google ADK?

Install the package with pip install google-adk. Then wrap your endpoint URL in StreamableHttpServerParameters and pass it to McpToolset.

Q: Can Google ADK restrict which Plaud tools execute?

Yes. Use the toolnames array when setting up the toolset to block operations like updatefile or deletefile.

Q: How do I assign the Plaud tools to my Google ADK agent?

Pass the configured toolset directly to the tools parameter when initializing your LlmAgent instance.

Feed Plaud meeting transcripts directly into Google ADK to process massive audio archives with Gemini.

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 Google ADK

Create your Vinkius account to connect Plaud to Google ADK — 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Dump Plaud audio into BigQuery

This Plaud integration lets you manage hundreds of hours of recorded calls sitting in your account. Connect this MCP Server to your Google ADK environment and let Gemini map it all out. The agent uses `list_files` to grab your catalog and `get_file_detail` to pull the metadata. From there, it pushes the structured data straight into your Google Cloud data warehouse. You do not have to write custom ETL pipelines. Your agent handles the extraction and formatting automatically.

Filter your MCP Server tools

Giving an autonomous system full delete access is usually a bad idea. Google's framework lets you restrict exactly what the agent can do. Use the `tool_names` filter to expose `get_transcript` and `get_summary` while hiding `delete_file`. This keeps your production environment safe. The agent gets the read-only access it needs to analyze conversations without the risk of accidentally wiping a crucial client recording.

Process massive contexts

Gemini handles over a million tokens without breaking a sweat. You can have your agent run `get_transcript` on twenty different hour-long meetings and dump the text directly into the prompt context. Then ask it to find contradictions across all those calls. It reads the raw text, cross-references everything, and gives you an answer. If it needs more context, it just calls `get_download_url` to grab the source MP3 links.

Setup guide

Set up Plaud MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Plaud tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Plaud_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Plaud tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the package with `pip install google-adk`. Then wrap your endpoint URL in `StreamableHttpServerParameters` and pass it to `McpToolset`.

Yes. Use the `tool_names` array when setting up the toolset to block operations like `update_file` or `delete_file`.

It thrives on them. Gemini's massive context window means you can feed it dozens of outputs from `get_transcript` simultaneously without hitting token limits.

Pass the configured toolset directly to the `tools` parameter when initializing your `LlmAgent` instance.

This integration touches highly sensitive voice memos and generated text summaries. Every request runs through an ephemeral V8 Isolate sandbox, ensuring your private meeting data vanishes the moment the connection drops.

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