How to Use the Plaud MCP in LlamaIndex

Q: How do I connect Plaud to LlamaIndex?

Install llama-index-tools-mcp. Set up a BasicMCPClient pointing to your MCP Server endpoint, wrap it with McpToolSpec, and call await mcptoolspec.totoollistasync() to get the functions.

Q: Can LlamaIndex update my Plaud meeting tags?

Yes. The updatefile tool allows your agent to modify tags and metadata. This is useful for marking files as indexed once they enter your vector database.

Q: How do I download the original audio through Plaud and LlamaIndex?

Your agent invokes getdownloadurl to grab the MP3 link. You can then write a custom function to download and store the actual audio file alongside your text embeddings.

Q: Can I delete old recordings after indexing them?

Absolutely. Call deletefile once the transcript is safely stored in your database. Just make sure your logic confirms the index update succeeded first.

Turn your Plaud meeting recordings into a searchable knowledge base using LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Plaud MCP to LlamaIndex

Create your Vinkius account to connect Plaud to LlamaIndex — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Plaud with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Index Plaud Audio with LlamaIndex

Stop searching through endless meeting notes. Your LlamaIndex application uses `list_files` to find every recording, then calls `get_transcript` to pull the raw conversation text. It embeds that text directly into your vector store via the MCP Server. Now your past conversations are fully queryable. When you ask a question, the engine retrieves the exact moments from the source data. You get answers grounded in what was actually said, not what the model guesses.

Semantic Search Across Summaries

Sometimes you just need the high-level decisions. You can configure your data pipeline to pull from `get_summary` instead of the full transcript. This keeps your index lean and focused on action items. If a query requires more context, the agent can dynamically call `get_file_detail` to check who attended or when the meeting happened. You control exactly what gets indexed using the `allowed_tools` filter on the MCP Server.

Dynamic Tag and Folder Routing

You don't have to dump everything into one giant index. Read the existing structure via `list_folders` and `list_tags`. You can route different departments' meetings into separate collections. If you need to fix metadata before indexing, `update_file` handles the changes. `McpToolSpec(client=mcp_client)` exposes all these operations natively to your FunctionAgent.

Setup guide

Set up Plaud 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 Plaud 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 Plaud tools.",
)
response = await agent.run("List recent Plaud 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 Plaud. 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 Plaud 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 Plaud MCP in LlamaIndex

Install `llama-index-tools-mcp`. Set up a `BasicMCPClient` pointing to your MCP Server endpoint, wrap it with `McpToolSpec`, and call `await mcp_tool_spec.to_tool_list_async()` to get the functions.

Yes. The `update_file` tool allows your agent to modify tags and metadata. This is useful for marking files as indexed once they enter your vector database.

Your agent invokes `get_download_url` to grab the MP3 link. You can then write a custom function to download and store the actual audio file alongside your text embeddings.

Absolutely. Call `delete_file` once the transcript is safely stored in your database. Just make sure your logic confirms the index update succeeded first.

Vinkius routes your raw transcripts and MP3 download URLs through a zero-trust architecture. The server requires just one endpoint token, and no conversational data is retained after the connection closes.

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