How to Use the Verbit MCP in CrewAI

Q: How does CrewAI manage Verbit's workflow?

You define the sequence. One agent creates the job using createjob, a second agent polls with getjob until completion, and a third retrieves results via gettranscript. The crew coordinates this entire multi-step process.

Run autonomous captioning and transcription operations using Verbit with CrewAI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Verbit MCP to CrewAI

Create your Vinkius account to connect Verbit 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 Verbit with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

MCP Server for Autonomous Transcription

You'll assign a specialized agent the task of calling `create_job`, uploading the media file. This initial action sets up the transcription job, and the agent then needs to monitor its status. The autonomous nature means one agent can oversee the entire process: creation, waiting, monitoring, and finally retrieval.

Monitoring Verbit Job Progress

A dedicated 'Monitor Agent' watches the job using `get_job`. This tool checks if the transcription is progressing or stalled. If the status check fails, a specialized agent can trigger an alert or retry the process. The shared memory allows the monitoring agent to pass the latest status directly to the action agent for the next step.

Retrieving Transcripts in CrewAI

Once confirmed complete, `get_transcript` retrieves the final caption data. This output is then passed as a document that other agents can analyze or act upon. The multi-agent system ensures that the transcript isn't just downloaded; it’s processed by specialized roles—like an 'Analyzer Agent'—right after retrieval.

Setup guide

Set up Verbit 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 Verbit tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You define the sequence. One agent creates the job using `create_job`, a second agent polls with `get_job` until completion, and a third retrieves results via `get_transcript`. The crew coordinates this entire multi-step process.

The core data type is the media file for input. The server outputs structured transcripts that your agents can then read and analyze using shared memory across the crew.

Yes, you pass the URL to the MCP Server specifically, or use `tool_filter` when setting up the advanced connection. This lets you expose only the necessary functions like `create_job`.

The monitoring agent can be tasked with checking failure states from `get_job`. It then triggers an escalation or retry sequence defined in the crew's collaborative rules.

Verbit processes media files and returns structured transcripts. The whole purpose is to move from raw media input to usable, readable text output.

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