How to Use the LiveKit MCP in CrewAI

Q: Can CrewAI agents collaborate on LiveKit tasks?

They can. With shared memory, one agent can initiate a createroom call and pass the room ID to another agent for participant management.

Q: How do I filter tools for a specific CrewAI agent?

Use the toolfilter feature in your client config to limit which tools an agent can access. This ensures your moderator agent can only perform safe actions.

Q: Does CrewAI support LiveKit egress monitoring?

Yes. Your crew can use listegress to track job status and alert you if a recording fails to start or finish.

Deploy autonomous CrewAI agents to manage LiveKit media sessions and handle complex participant egress.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LiveKit MCP to CrewAI

Create your Vinkius account to connect LiveKit 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 LiveKit with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous CrewAI media monitoring

Assign a monitor agent to watch room status using `list_rooms` and `list_participants`. If the agent detects an empty room, it triggers `delete_room` to clean up resources. This creates a self-managing system that keeps your infrastructure costs low. You don't need to write custom scripts to track session health.

Specialized CrewAI egress agents

Have one agent manage `start_web_egress` while another validates the stream quality. The agents work together to ensure your recordings are captured correctly every time. This division of labor allows for more complex setups than a single script could handle. You can even have an agent update the stream output URL on the fly.

Dynamic SIP call management

Let your agents handle incoming calls using `create_sip_dispatch_rule` based on real-time demand. If a specific area code sees high volume, the agent can provision new numbers automatically. It turns your telephony management into an active, responsive process. Your crew handles the load without requiring human oversight.

Setup guide

Set up LiveKit 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 LiveKit tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

They can. With shared memory, one agent can initiate a `create_room` call and pass the room ID to another agent for participant management.

Use the tool_filter feature in your client config to limit which tools an agent can access. This ensures your moderator agent can only perform safe actions.

Yes. Your crew can use `list_egress` to track job status and alert you if a recording fails to start or finish.

Vinkius manages the endpoint security. You can add extra safety by limiting the agent's permissions through the MCP interface.

The agents only see the room metadata, participant lists, and trunk configurations. They do not access the raw audio or video streams during their operation.

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