How to Use the Dyte MCP in CrewAI

Q: How do I filter Dyte tools for specific CrewAI agents?

Use the toolfilter argument within the MCPServerHTTP setup. This allows you to restrict an agent to only specific tools like listparticipants.

Build autonomous video operations with CrewAI. Let specialized agents manage meeting lifecycles, recordings, and participants.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dyte MCP to CrewAI

Create your Vinkius account to connect Dyte 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 Dyte with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

CrewAI agents managing Dyte sessions

Assign a dedicated agent to handle video infrastructure. This agent uses `create_meeting` and `get_meeting` to keep the crew informed about active sessions. By delegating these tasks, your other agents focus on analysis or participant interaction. The shared memory allows them to coordinate without manual intervention.

Automated monitoring of Dyte livestreams

Station an agent to watch your livestream status. It calls `start_livestream` and `stop_livestream` based on the meeting schedule, ensuring your broadcast starts and ends on time. This prevents human error in live environments. The agent operates autonomously, reacting to meeting lifecycle events as they occur in real-time.

Detailed participant reporting

Use a specialized agent to audit your video sessions. It runs `list_participants` to track attendance and updates your internal records with the session data. This provides a clear view of meeting participation. The agent handles the audit trail, letting you focus on the results rather than the data collection.

Setup guide

Set up Dyte 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 Dyte tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Yes, by including the Dyte MCP server in your agent's tool list. The agent decides when to call `create_meeting` based on its assigned objectives.

Use the `tool_filter` argument within the `MCPServerHTTP` setup. This allows you to restrict an agent to only specific tools like `list_participants`.

They will share meeting data through CrewAI's shared memory. Once one agent creates a meeting, the others have access to the ID for their specific tasks.

The Vinkius environment isolates your session tokens and meeting metadata. Every request is authenticated through an ephemeral endpoint token, preventing unauthorized access.

Your agents can include logic to verify the recording status after calling `start_recording`. If the tool returns an error, the agent can attempt to fix the state.

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