How to Use the Maestra MCP in LlamaIndex

Q: How does LlamaIndex ingest transcripts from Maestra?

The framework uses exporttranscriptionresults to fetch the raw text output from your completed jobs. LlamaIndex then parses this text into document nodes for embedding and indexing.

Q: Can I use LlamaIndex to query my Maestra media library?

Yes, you can query your library by loading metadata from listmaestrafiles into a vector index. This allows you to find files using semantic search queries rather than exact file names.

Q: How do I verify if a Maestra video is ready to index in LlamaIndex?

You call getfiledetails to check the processing status of the target file. Your LlamaIndex ingestion script runs this check to ensure it only reads fully completed transcripts.

Q: Does this Maestra MCP Server support translation queries inside LlamaIndex?

Yes, you run translatetranscription to generate localized versions of your media files. LlamaIndex then indexes these translated versions to support multi-lingual RAG applications.

Index transcripts and voiceover metadata into LlamaIndex vector stores using the Maestra MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Maestra MCP to LlamaIndex

Create your Vinkius account to connect Maestra 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 Maestra with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live transcripts directly into LlamaIndex RAG

`export_transcription_results` fetches completed text files from your account so your LlamaIndex pipeline can ingest them. The framework chunks this text and embeds it into your vector database via the MCP interface. By calling `get_file_details`, the ingestion pipeline checks if a file is fully processed before attempting to index it. This prevents empty documents or partial transcripts from polluting your index.

Search and query your Maestra media directory

`list_maestra_files` acts as a data connector, pulling your entire catalog of audio and video metadata into LlamaIndex. Your agent searches across this metadata to find specific files without loading raw media. To keep your index structured, `list_account_folders` maps your cloud directory layout to your vector store collections. Restricting semantic searches to specific project folders becomes trivial once this mapping is active.

Synthesize voiceovers from LlamaIndex query results

`generate_ai_voiceover` creates new synthetic audio based on the text retrieved from your LlamaIndex knowledge base. You feed the synthesized query response back into this tool to output spoken audio. Before generating the audio, `list_available_ai_voices` queries the server for compatible voice models. This step ensures the generated voice matches the language of your indexed documents.

Setup guide

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

The framework uses `export_transcription_results` to fetch the raw text output from your completed jobs. LlamaIndex then parses this text into document nodes for embedding and indexing.

Yes, you can query your library by loading metadata from `list_maestra_files` into a vector index. This allows you to find files using semantic search queries rather than exact file names.

You call `get_file_details` to check the processing status of the target file. Your LlamaIndex ingestion script runs this check to ensure it only reads fully completed transcripts.

Yes, you run `translate_transcription` to generate localized versions of your media files. LlamaIndex then indexes these translated versions to support multi-lingual RAG applications.

Your transcripts and media metadata are processed through sandboxed V8 isolates on Vinkius. The Maestra MCP Server never exposes your source audio files or text contents to external databases during the indexing loop.

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