How to Use the Deepgram MCP in CrewAI

Q: Can I build a self-monitoring system for Deepgram usage with CrewAI?

Definitely. Assign an agent the getprojectusage tool and give it a recurring task to check your balance. You can have it delegate to another agent to send notifications if usage hits a certain threshold.

Deploy a crew of AI agents to transcribe, analyze, and report on audio data using Deepgram tools and CrewAI.

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 CrewAI

Create your Vinkius account to connect Deepgram to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble an Audio Processing Crew

CrewAI lets you build teams of specialized agents. You can create a 'Transcriptionist Agent' and give it exclusive access to the `transcribe_audio_url` tool. It processes audio files and passes the text to an 'Analyst Agent'. That second agent's job is to read the transcript, identify key topics, and then pass a summary to a 'Writer Agent' for final reporting. This division of labor is CrewAI's strength, and this MCP Server provides the focused tools each agent needs to do its job.

Build Autonomous Monitoring Agents

Set up a 'Guardian Agent' whose only job is to watch your Deepgram account. Using the `get_project_usage` tool, it can periodically check your credit usage. You define the task and the schedule, and the agent runs autonomously. If credits fall below a certain level, the Guardian Agent can delegate a task to a 'Notifier Agent' to send an alert. This is how you build a hands-off, self-managing system for your infrastructure with CrewAI.

A Content Creation Team with This MCP Server

Imagine a crew for creating audio content. A 'Researcher Agent' gathers information. A 'Scriptwriter Agent' turns it into a narrative. Finally, a 'Voiceover Agent' equipped with the `convert_text_to_speech` tool generates the final audio file. By assigning specific tools and roles, you create an automated production line. Each agent in the crew focuses on one part of the process, collaborating to get the job done without you intervening at every step.

Setup guide

Set up Deepgram MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Deepgram tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Deepgram Analyst",
    goal="Access and analyze Deepgram data via MCP.",
    backstory="Expert analyst with direct Deepgram access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Deepgram transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Deepgram Analyst",
        goal="Access and analyze Deepgram data via MCP.",
        backstory="Expert analyst with direct Deepgram access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Deepgram transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

When you define an Agent in CrewAI, you can pass a list of tool objects. You can get these tools from the MCP client and filter them, so your 'transcriber' agent only gets the `transcribe_audio_url` tool, for example.

Yes. You'd create a two-agent crew. The first agent uses the `transcribe_audio_url` tool. The second agent takes the text output from the first and performs the summarization task.

For a simple setup, you can pass the Vinkius URL directly into the `mcps` parameter when you instantiate your Agent. CrewAI handles the connection and tool discovery from there.

Definitely. Assign an agent the `get_project_usage` tool and give it a recurring task to check your balance. You can have it delegate to another agent to send notifications if usage hits a certain threshold.

Your agents will handle audio file URLs and text for speech generation. Every API call from your CrewAI agent to the Vinkius MCP server is executed in a fresh, isolated V8 sandbox that is destroyed after the request. Your data is not persisted.

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