How to Use the AssemblyAI MCP in Google ADK

Q: Can my Google ADK agent detect topics using AssemblyAI?

Yes. It runs gettopics on the completed job ID. Gemini can then map those topics to your internal taxonomy stored in Google Cloud.

Q: Does the Google ADK agent wait for the AssemblyAI audio to finish processing?

It polls gettranscript until the status shows completion. You can write custom ADK logic to handle timeouts or retries if the file is massive.

Q: Can I limit which tools the agent accesses?

You can. Use the toolnames filter when setting up the toolset. This restricts the agent to specific actions like listtranscripts while blocking deletions.

Feed massive audio transcripts directly into Gemini using the AssemblyAI MCP Server for Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AssemblyAI MCP to Google ADK

Create your Vinkius account to connect AssemblyAI to Google ADK 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 AssemblyAI with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Transcribe audio for Gemini 1.5 Pro

Google ADK agents thrive on massive context windows. You can feed hours of audio to `transcribe_audio_url` and let Gemini read the entire output. The agent fetches the result via `get_transcript` and pushes it straight into your Vertex AI pipeline. You do not need to build custom ingestion scripts. The MCP integration handles the connection to Vinkius natively. Your Gemini agent reads the audio text and cross-references it with your existing BigQuery datasets in a single step.

Extract insights with this MCP Server

Raw transcription is just the starting point. Your agent calls `get_summary` to distill a two-hour all-hands meeting into a tight paragraph. It then runs `get_chapters` to break the recording into searchable segments. These tools feed perfectly into Google's enterprise ecosystem. The agent can take the output from `get_sentiments` and write the emotional analysis directly to a Cloud SQL database. You push structured voice analytics straight into your existing infrastructure.

Track speakers and manage files

Multi-speaker meetings get confusing fast. Your agent uses `get_speakers` to assign specific labels to every voice in the file. Gemini uses those labels to understand who committed to which action item during the call. Keeping your workspace organized matters. The agent can check your history with `list_transcripts` and remove outdated files using `delete_transcript`. You maintain total control over your audio storage directly from your Python code.

Setup guide

Set up AssemblyAI 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 AssemblyAI 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="AssemblyAI_agent",
    model="gemini-2.0-flash",
    instruction="You have access to AssemblyAI 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 AssemblyAI. 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 AssemblyAI 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 AssemblyAI MCP in Google ADK

Initialize an McpToolset with your Vinkius HTTP endpoint. Pass that toolset into your LlmAgent configuration. Gemini will instantly see all the transcription operations.

Yes. It runs `get_topics` on the completed job ID. Gemini can then map those topics to your internal taxonomy stored in Google Cloud.

It polls `get_transcript` until the status shows completion. You can write custom ADK logic to handle timeouts or retries if the file is massive.

You can. Use the tool_names filter when setting up the toolset. This restricts the agent to specific actions like `list_transcripts` while blocking deletions.

Vinkius processes your audio URLs, speaker labels, and sentiment data inside a zero-trust V8 Isolate. The environment spins up just for your request and dies immediately after. Nobody at Google or Vinkius can peek at your company meetings.

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