How to Use the Deepgram MCP in AutoGen

Q: How do I add Deepgram to my AutoGen setup?

Install the autogen-extmcp plugin. Calling mcpservertools with your endpoint URL lets you pass the list directly to your AssistantAgent constructor.

Give your AutoGen agents the ability to debate Deepgram audio transcripts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deepgram MCP to AutoGen

Create your Vinkius account to connect Deepgram 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 Deepgram with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Transcribe and debate audio evidence

Single agents miss context. One AutoGen persona can run `transcribe_url` on a customer support call while another analyzes the text for compliance violations. They discuss these findings in real time. Disagreements over sentiment force them to negotiate until reaching a consensus. Once settled, a third agent uses `speak_text` to generate a voice summary of their final decision.

Negotiate API access dynamically

Handing out permanent API credentials creates massive security holes. A developer bot might request access to test a new feature, prompting the security persona to evaluate the risk. Approval triggers the system to call `create_key` for a temporary token. The security monitor watches the clock and executes `delete_key` the second that testing window closes.

Audit Deepgram MCP Server costs collaboratively

Cost overruns happen when teams operate in silos. Your finance agent pulls `get_usage` metrics while the operations counterpart checks `list_projects` to map resource allocation. These two personas argue over budget limits based on hard numbers. Spotting a project that burns too much cash leads them to throttle its Deepgram MCP Server access automatically.

Setup guide

Set up Deepgram 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 Deepgram 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="Deepgram_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the autogen-ext[mcp] plugin. Calling mcp_server_tools with your endpoint URL lets you pass the list directly to your AssistantAgent constructor.

They excel at it. One bot handles the API execution while others review the output, challenge inaccuracies, and finalize the summary.

Yes, it works entirely in the background. You skip writing custom JSON definitions for every single audio or billing endpoint.

Assign the key management tools to a specific security persona. That specialized bot evaluates requests from other agents before generating or revoking access.

Every tool execution happens inside a strictly isolated Vinkius container. Raw voice data and generated transcripts pass through a secure tunnel that drops all state the moment the conversation ends.

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