Bring Webrtc
to CrewAI
Learn how to connect LiveKit to CrewAI and start using 41 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the LiveKit MCP Server?
Connect your LiveKit infrastructure to any AI agent to orchestrate real-time communication environments through natural language. This server provides comprehensive control over WebRTC sessions, participant permissions, and media recording.
What you can do
- Room Lifecycle — Create, list, and delete rooms with custom timeouts, participant limits, and metadata.
- Participant Control — List active participants, retrieve detailed info, or remove users from a session.
- Media Management — Remotely mute or unmute specific tracks (audio/video) for any participant.
- Real-time Data — Send data packets (Base64 encoded) to specific participants or entire rooms for custom signaling.
- Recording & Egress — Start room-wide recordings using web layouts or record specific web pages via the Egress API.
- Metadata & Permissions — Update room-wide metadata or modify individual participant permissions and subscriptions on the fly.
How it works
- Subscribe to this server
- Enter your LiveKit Server URL and API Token/Secret
- Start managing your real-time infrastructure from Claude, Cursor, or any MCP-compatible client
No more manual dashboard navigation to check who is in a room or to force-mute a noisy participant. Your AI acts as a real-time session administrator.
Built-in capabilities (41)
Explicitly trigger a named agent to join a specific room
Provision an ingress point (RTMP, WHIP, or URL pull)
Create a room with specific settings
Map incoming calls to specific rooms based on phone numbers or pins
Define how incoming SIP calls are handled
Define a trunk for dialing out
Dial a SIP number and bring them into a LiveKit room
Remove a dispatch rule
Remove an ingress point
Forcibly disconnect all participants and delete the room
Remove a SIP dispatch rule
Remove a SIP trunk configuration
Get info for a specific participant
List dispatches for a room
List active egress jobs
List provisioned ingresses
List participants in a room
List numbers owned by the project
List active/open rooms
List configured SIP inbound trunks
List configured SIP outbound trunks
Mute/unmute a participant's track
Buy a number and optionally assign a SIP dispatch rule
Release a number back to the inventory
Kick a participant from a room
Search for available numbers by country/area code
Send data packets to participants
Record a specific participant's audio and video
Record an entire room using a web layout
Record one audio and one video track together
Export a single track without transcoding
Record any web page
Stop an active egress
Transfer an active SIP call to another number or URI
Update room or participant settings for a reusable ingress
Change the web layout of an active RoomComposite egress
Update metadata or permissions for a participant
Change the dispatch rule for a number
Update room-wide metadata
Add/remove RTMP/SRT output URLs from an active stream
Subscribe/unsubscribe a participant from specific tracks
Why CrewAI?
When paired with CrewAI, LiveKit becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call LiveKit tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.
- —
Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools
- —
CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the
mcpsparameter and agents auto-discover every available tool at runtime - —
Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls
- —
Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports
LiveKit in CrewAI
LiveKit and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect LiveKit to CrewAI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for LiveKit in CrewAI
The LiveKit MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 41 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in CrewAI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
LiveKit for CrewAI
Every tool call from CrewAI to the LiveKit MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I remotely mute a participant who has background noise?
Yes. Use the mute_published_track tool by providing the room name, participant identity, and the specific track SID. You can set the muted boolean to true to silence them immediately.
Is it possible to record a session for later viewing?
Absolutely. You can use start_room_composite_egress to record an entire room using a web layout, or start_web_egress to record a specific URL. These tools leverage LiveKit's Egress service.
How do I kick a disruptive user from a room?
You can use the remove_participant tool. Simply provide the room name and the identity of the participant you wish to disconnect.
How does CrewAI discover and connect to MCP tools?
CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.
Can different agents in the same crew use different MCP servers?
Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.
What happens when an MCP tool call fails during a crew run?
CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.
Can CrewAI agents call multiple MCP tools in parallel?
CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.
Can I run CrewAI crews on a schedule (cron)?
Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.
MCP tools not discovered
Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.
Agent not using tools
Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".
Timeout errors
CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.
Rate limiting or 429 errors
Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.
Explore More MCP Servers
View all →
Clari
8 toolsManage revenue intelligence and forecasting via Clari — track opportunities, monitor forecasts, and audit pipeline changes directly from any AI agent.
Rocketlane
11 toolsDeliver customer onboarding projects on time with collaborative workspaces, task tracking, and time-to-value analytics.
Agile CRM
4 toolsSales and marketing automation — manage contacts, deals, tasks, and campaigns via AI.
MonkeyLearn
10 toolsAnalyze and extract data from text via MonkeyLearn — sentiment analysis and keyword extraction directly from your AI agent.