How to Use the Speechnotes MCP in AutoGen

Q: How does Speechnotes work with AutoGen?

Your agents don't just call tools; they debate how and when to call them. The MCP Server provides the actions, and AutoGen manages the multi-agent conversation needed to reach a consensus decision.

Q: What should I use in AutoGen for Speechnotes authentication?

Always start by having an agent run testspeechnotesauth. This acts as the initial 'System Check' debate, ensuring all other agents know that the connection is good to go before any work starts.

Simulate decision-making between multiple agents using Speechnotes and AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Speechnotes MCP to AutoGen

Create your Vinkius account to connect Speechnotes 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 Speechnotes with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Debating Transcription Results with the MCP Server

The process starts by calling `transcribe_audio_url`. You can assign one agent to perform this action. A second agent—maybe a 'Verification Agent'—then checks the data using `get_transcription_status` before declaring the result final. The core value here is debate: the agents discuss whether the job has finished, leading to a consensus decision that you execute programmatically.

Security and Validation in AutoGen

You can assign an agent role dedicated purely to security. This agent must check the payload using `generate_webhook_signature` before any other agent accepts the data. It ensures that every piece of information coming into your conversation is valid. Another agent might run `get_remaining_credits`, forcing a debate on whether the requested action is even affordable, making resource management part of the decision process.

Managing and Exporting Data for Multi-Agent Flows

After the agents converge on an answer, you need the final data. The 'Output Agent' can call `get_transcription_export` to pull the finalized text in a clean format. This output is then passed back into the agent pool for final review. If the conversation fails or needs restarting, you can use `list_transcription_history` so that an 'Archivist Agent' knows exactly what was attempted previously.

Setup guide

Set up Speechnotes 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 Speechnotes 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="Speechnotes_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

    result = await agent.run("List recent Speechnotes 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 Speechnotes. 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 Speechnotes 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 Speechnotes MCP in AutoGen

Your agents don't just call tools; they debate *how* and *when* to call them. The MCP Server provides the actions, and AutoGen manages the multi-agent conversation needed to reach a consensus decision.

Always start by having an agent run `test_speechnotes_auth`. This acts as the initial 'System Check' debate, ensuring all other agents know that the connection is good to go before any work starts.

You assign a dedicated 'Finance Agent' whose sole job is to call `get_remaining_credits`. This agent forces the group to confirm budget availability before any expensive transcription jobs are initiated.

This server interacts with audio files, job records, and usage statistics. When AutoGen processes these types of structured data, it's crucial that the agents respect the sensitive nature of the underlying information.

Yes. You can set up a webhook listener agent. When a job completes, the incoming payload triggers that agent, which then brings fresh data into the ongoing conversation for the group to debate.

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