Bring Webrtc
to LangChain
Learn how to connect Daily.co to LangChain and start using 50 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 Daily.co MCP Server?
Connect your Daily.co account to any AI agent to orchestrate real-time video and audio communication workflows through natural language.
What you can do
- Room Management — Create, list, update, and delete video rooms. Configure privacy settings (public/private) and custom properties on the fly.
- Participant Control — Monitor real-time presence to see who is in a call and eject participants or ban them when necessary.
- Domain Configuration — Retrieve and set top-level domain settings for your Daily infrastructure.
- Session Data — Sync and retrieve custom session data across all participants to maintain state during meetings.
- App Messaging — Send data payloads to participants within a room to trigger client-side actions or notifications.
How it works
- Subscribe to this server
- Enter your Daily API Key
- Start managing your video infrastructure from Claude, Cursor, or any MCP-compatible client
Your AI acts as a virtual operator, capable of spinning up meeting rooms for support tickets or auditing active sessions without you ever touching a dashboard.
Who is this for?
- Developers — quickly test room configurations and manage WebRTC infrastructure directly from the code editor.
- Support & Ops Teams — monitor active meeting presence and manage participant access for webinars or private consultations.
- Product Managers — automate the creation of unique meeting links for specific project workflows or client calls.
Built-in capabilities (50)
Purchase a specific or random number
Submit a batch processor job
Create a meeting token
Create a new room
Create a webhook
Delete a batch job
Delete a recording reference
Delete a room
Delete a webhook
Kick participants from a room
Get batch job status
Get download links for finished jobs
Retrieve domain configuration
List all active participants on the domain
Retrieve detailed call logs and metrics
Get details for a specific session
List participants in a session
Get recording information
Generate a time-limited S3 download link
Retrieve a specific room
Get active participants in a room
Retrieve meeting session data
Get specific webhook info
Search for numbers by areacode or region
List all batch jobs
List meeting sessions
List numbers owned by your domain
Supports pagination. List cloud recordings
Supports pagination. List rooms
List webhooks
Release a number
Send data to participants
Send DTMF tones to a session
Set domain configuration
Sync data to all participants
Call a sipUri or phoneNumber
Start RTMP/HLS streaming
Start a recording
Start real-time transcription
End a dial-out session
Stop streaming
Stop an active recording
Stop transcription
Update layout or endpoints for streaming
Update participant permissions
Update layout of an active recording
Modify room privacy or configuration
Update participants being transcribed
Update or re-activate a failed webhook
Validate a meeting token
Why LangChain?
LangChain's ecosystem of 500+ components combines seamlessly with Daily.co through native MCP adapters. Connect 50 tools via Vinkius and use ReAct agents, Plan-and-Execute strategies, or custom agent architectures. with LangSmith tracing giving full visibility into every tool call, latency, and token cost.
- —
The largest ecosystem of integrations, chains, and agents. combine Daily.co MCP tools with 500+ LangChain components
- —
Agent architecture supports ReAct, Plan-and-Execute, and custom strategies with full MCP tool access at every step
- —
LangSmith tracing gives you complete visibility into tool calls, latencies, and token usage for production debugging
- —
Memory and conversation persistence let agents maintain context across Daily.co queries for multi-turn workflows
Daily.co in LangChain
Daily.co and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Daily.co to LangChain 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 Daily.co in LangChain
The Daily.co 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 50 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in LangChain 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
Daily.co for LangChain
Every tool call from LangChain to the Daily.co MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I see exactly who is currently inside a video room?
Yes. Use the get_room_presence tool with the room name. It returns a snapshot of all active participants currently connected to that specific session.
How do I create a private room that requires a token to join?
You can use the create_room tool and set the privacy parameter to 'private'. You can also pass additional configuration in the properties JSON field.
Is it possible to remove a disruptive participant from a call?
Yes. The eject_participants tool allows you to kick specific users by their IDs. You can also set the ban flag to true to prevent them from re-entering the room.
How does LangChain connect to MCP servers?
Use langchain-mcp-adapters to create an MCP client. LangChain discovers all tools and wraps them as native LangChain tools compatible with any agent type.
Which LangChain agent types work with MCP?
All agent types including ReAct, OpenAI Functions, and custom agents work with MCP tools. The tools appear as standard LangChain tools after the adapter wraps them.
Can I trace MCP tool calls in LangSmith?
Yes. All MCP tool invocations appear as traced steps in LangSmith, showing input parameters, response payloads, latency, and token usage.
MultiServerMCPClient not found
Install: pip install langchain-mcp-adapters
Explore More MCP Servers
View all →
Ada
4 toolsAI-powered customer service automation — manage conversations, end users, and knowledge via AI.
Evernest Property Management
10 toolsEquip your AI agent to manage rental properties, track tenants, and monitor maintenance via the Evernest API.
OECD Data API
3 toolsAccess global economic data — audit social and fiscal series via AI.
Baserow
10 toolsManage no-code databases via Baserow — list tables, query rows, create records and manage schemas from any AI agent.