How to Use the Freesound MCP in Google ADK

Q: How do I connect the Freesound MCP Server to Google ADK?

Use pip install google-adk and set up a McpToolset. Pass the StreamableHttpServerParameters with your endpoint URL directly into your LlmAgent tools list.

Q: Can Google ADK restrict which Freesound MCP tools my agent sees?

Yes. You can use the toolnames filter when initializing the toolset. This prevents your agent from calling uploadsound if you only want it to search.

Q: How does the agent find specific Freesound creators?

It uses the getuser tool to pull creator profiles. It can then chain that with getusersounds to map out their entire upload history.

Give your Google ADK agents direct access to Freesound. Search, download, and manage audio packs using Gemini's massive context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freesound MCP to Google ADK

Create your Vinkius account to connect Freesound 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 Freesound with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Freesound packs with Google ADK

The `get_pack` tool extracts every piece of metadata tied to a specific Freesound collection. Your agent pulls the entire tracklist, creator details, and file specifications in a single pass. Gemini models hold millions of tokens. You can feed the results of `get_user_sounds` and `get_pack` directly into the context window. Your agent cross-references massive audio catalogs against your internal BigQuery datasets to find exact matches for your enterprise projects.

Execute complex Solr-style queries

The `search_sounds` tool translates natural language requests into strict database filters. Your agent queries the Freesound catalog for specific frequencies, durations, or licensing requirements. Enterprise systems demand exact parameters. By wrapping this MCP Server in a `McpToolset`, you expose these search capabilities directly to your `LlmAgent`. The agent navigates the results and isolates the exact files you need for your Vertex AI workflows.

Acquire uncompressed audio files

The `download_sound` tool fetches the original, high-quality asset from the database. Your agent identifies the target ID and streams the file into your Google Cloud storage buckets. You skip the manual browsing phase completely. Before pulling the trigger on a massive download, your agent uses `get_sound` to inspect the sample rate. It only acquires files that meet your strict production standards.

Setup guide

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

Use `pip install google-adk` and set up a `McpToolset`. Pass the `StreamableHttpServerParameters` with your endpoint URL directly into your `LlmAgent` tools list.

Yes. You can use the `tool_names` filter when initializing the toolset. This prevents your agent from calling `upload_sound` if you only want it to search.

It uses the `get_user` tool to pull creator profiles. It can then chain that with `get_user_sounds` to map out their entire upload history.

Exactly. You can pull massive lists of search results via the MCP Server and let Gemini sort them in memory before making a final selection.

This integration touches your private sound metadata and moderation queues via `get_pending_uploads`. Vinkius isolates the entire execution within a zero-trust environment, ensuring no cross-contamination with other cloud processes.

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