How to Use the Freesound MCP in AutoGen

Q: How do I search for sounds using Freesound within an AutoGen agent?

You define the searchsounds tool in your assistant agent's configuration. The agent will then invoke it whenever it needs to find new audio assets.

Q: Can AutoGen agents coordinate on Freesound downloads?

Yes, you can assign the downloadsound tool to a specific agent. Other agents can then request that it perform the download once they agree on the target file.

Debate and refine your audio asset selection with the Freesound MCP Server and AutoGen multi-agent workflows.

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 AutoGen

Create your Vinkius account to connect Freesound to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Negotiate sound choices between agents

Set up a research agent to call `search_sounds` while a critic agent checks the results. They discuss which files meet your project's aesthetic criteria before selecting the final asset. This prevents bad downloads. The agents won't call `download_sound` until they reach a consensus on the best file for your specific needs.

Verify file quality with multi-agent checks

One agent acts as a quality controller using `get_sound` to inspect sample rates and bit depths. It challenges the search agent if the technical specs don't meet your standard. This ensures you only get high-fidelity files. The agents perform the due diligence so you don't have to audit every single file yourself.

Coordinate complex asset collections

Have your agents work together to build a sound pack using `get_pack`. They can identify missing elements and search for complementary sounds to complete the set. This is more than just a search tool. It's a team of agents managing your audio library and ensuring your project has the right assets.

Setup guide

Set up Freesound 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 Freesound 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="Freesound_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Freesound 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="Freesound_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Freesound 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 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 AutoGen

You define the `search_sounds` tool in your assistant agent's configuration. The agent will then invoke it whenever it needs to find new audio assets.

Yes, you can assign the `download_sound` tool to a specific agent. Other agents can then request that it perform the download once they agree on the target file.

Absolutely. You can provide the tools to multiple agents, allowing them to compare findings and debate which audio files are the best fit.

You can write a custom supervisor agent that monitors the API response. It can pause requests if it detects that the limit is approaching.

Your auth token is passed directly to the MCP server. We keep no record of your account details, and all communication between agents is ephemeral.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python