How to Use the Daily.co MCP in LlamaIndex

Q: Can I index Daily.co meeting recordings directly into LlamaIndex?

Yes. The Daily.co MCP Server provides the metadata via listrecordings, and you can use the resulting download links to pull files into your document loaders for vector ingestion.

Q: How do I set up the Daily.co tool spec inside LlamaIndex?

Install llama-index-tools-mcp and initialize the basic MCP client. From there, register the tools with McpToolSpec and pass them to your agent.

Q: Does LlamaIndex support filtering which Daily.co tools my agent can use?

Yes. You can use the allowedtools filter when setting up the MCP tool spec to restrict your agent to specific operations like room creation.

Q: How do I handle large domains with hundreds of active rooms?

Use listrooms which supports pagination natively. The tool retrieves your inventory in chunks, preventing your agent from hitting token limits or API rate caps during indexing.

Index your Daily.co meeting data directly into LlamaIndex to build a searchable knowledge base of your live video sessions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Daily.co MCP to LlamaIndex

Create your Vinkius account to connect Daily.co to LlamaIndex 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 Daily.co with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build searchable indexes from live meeting logs

The `get_logs` tool pulls detailed session metrics and call data directly into your LlamaIndex pipelines. Your agent indexes these logs into your vector store, making technical call performance and participant histories instantly searchable. Instead of guessing why a call dropped, you query your index. The agent retrieves the exact log details, correlates them with past sessions, and gives you answers grounded in actual API telemetry.

Ground your RAG applications in active room configurations

The `list_rooms` tool retrieves your complete room inventory and feeds it directly into your knowledge index. Your RAG system uses this data to answer queries about active room settings, privacy configurations, and active domain rules. By coupling this with `get_room`, your agent checks the exact state of specific rooms before suggesting modifications. This prevents your agent from hallucinating room configurations or trying to modify non-existent meetings.

Query live participant presence using LlamaIndex

The `get_global_presence` tool monitors who is currently active across your entire Daily.co domain. LlamaIndex indexes this presence data in real-time, allowing you to run semantic queries on active team collaboration. You can ask your agent who is currently in a meeting or check active room densities. The agent queries the live tool, updates its local index, and delivers an accurate snapshot of your domain's live activity.

Setup guide

Set up Daily.co MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Daily.co MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Daily.co tools.",
)
response = await agent.run("List recent Daily.co data")

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 Daily.co. 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 Daily.co 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 Daily.co MCP in LlamaIndex

Yes. The Daily.co MCP Server provides the metadata via `list_recordings`, and you can use the resulting download links to pull files into your document loaders for vector ingestion.

Install `llama-index-tools-mcp` and initialize the basic MCP client. From there, register the tools with `McpToolSpec` and pass them to your agent.

Yes. You can use the `allowed_tools` filter when setting up the MCP tool spec to restrict your agent to specific operations like room creation.

Use `list_rooms` which supports pagination natively. The tool retrieves your inventory in chunks, preventing your agent from hitting token limits or API rate caps during indexing.

All telemetry and presence data fetched by this MCP Server is processed entirely in memory within an isolated V8 sandbox. No log data or participant identifiers are stored on our servers.

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