How to Use the AssemblyAI MCP in CrewAI

Q: Can I limit which CrewAI agents can delete files in AssemblyAI?

Yes, you use the MCP server configuration and a toolfilter to restrict access. You can allow your CrewAI Compliance Agent to use deletetranscript while preventing your Analyst Agents from touching it.

Q: Can I extract AssemblyAI structured paragraphs for CrewAI analysis?

Yes, your CrewAI agents can call gettranscriptparagraphs to break down long recordings. This allows them to analyze the AssemblyAI conversation structure and identify speaker transitions more accurately.

Deploy a crew of specialized AI agents to transcribe, analyze, and audit audio files using CrewAI and AssemblyAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AssemblyAI MCP to CrewAI

Create your Vinkius account to connect AssemblyAI 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 AssemblyAI with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Delegate audio tasks across a specialized CrewAI team

Instead of one agent doing everything, you assign specific AssemblyAI tools to specialized CrewAI team members. Your Transcriber Agent uses `transcribe_audio` to kick off the job, while your Auditor Agent polls `get_transcript` to verify the output. This division of labor keeps your CrewAI agents focused on single transcription tasks. The Auditor doesn't need to know how to upload files; it only cares about analyzing the AssemblyAI text once the Transcriber finishes its job.

Run CrewAI audits on AssemblyAI transcript sentences

Analyzing a massive wall of AssemblyAI text is difficult for a single CrewAI agent. By using `get_transcript_sentences`, your CrewAI supervisor can split the transcript and assign different sentence blocks to multiple Analyst Agents. One CrewAI agent can look for compliance violations, another can flag customer sentiment, and a third can extract action items from the AssemblyAI sentences. The CrewAI agents compile their findings into a single report, saving time and tokens.

Enforce CrewAI data hygiene policies on AssemblyAI

This MCP Server allows you to task a specialized Compliance Agent with running `delete_transcript` the moment the final report is generated. Because CrewAI supports sequential execution, this cleanup step is guaranteed to run only after all other agents have successfully completed their analysis and saved their outputs. Your AssemblyAI workspace remains clutter-free without manual intervention.

Setup guide

Set up AssemblyAI 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 AssemblyAI tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent AssemblyAI 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="AssemblyAI Analyst",
        goal="Access and analyze AssemblyAI data via MCP.",
        backstory="Expert analyst with direct AssemblyAI access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent AssemblyAI 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 AssemblyAI. 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 AssemblyAI 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 AssemblyAI MCP in CrewAI

You can pass your Vinkius endpoint URL directly to the agent's MCP configuration list. This gives that specific CrewAI agent access to tools like `transcribe_audio` without exposing them to the rest of the crew.

Yes, you use the MCP server configuration and a `tool_filter` to restrict access. You can allow your CrewAI Compliance Agent to use `delete_transcript` while preventing your Analyst Agents from touching it.

Your Transcriber Agent starts the job and passes the ID to your Auditor Agent. The Auditor then uses `get_transcript` to poll for completion, allowing the CrewAI team to work asynchronously.

Yes, your CrewAI agents can call `get_transcript_paragraphs` to break down long recordings. This allows them to analyze the AssemblyAI conversation structure and identify speaker transitions more accurately.

All CrewAI transcription requests and text outputs are routed through secure, short-lived V8 isolates. Your sensitive media files and text records are never stored on Vinkius, maintaining direct, encrypted transit to AssemblyAI.

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